Local GPU Infrastructure Docs Local GPU Infrastructure

IdealTech RTX 5090 ComfyUI service-node purchase decision#

Status: Hardware decision retained; procurement route reopened on 2026-09-22 Decision date: 2026-09-22 Lane-topology addendum: 2026-09-23; optional CPU-direct Gen5 OS-drive upgrade investigated and rejected at current cost; retaining the RTX 5090 at PCIe 5.0 x16 is a hard requirement Power addendum: 2026-09-23; 1200 W retained, same-price peers audited, Corsair HX1200i made the value default under a quote gate, and UPS purchase deferred pending power-quality evidence Scope: Second Malaysian RTX 5090 worker purchased through IdealTech for ComfyUI-as-a-service Retailer-package ceiling: RM38,647, including a separate 1 TB OS drive

Context#

Malaysian retailers were requiring an RTX 5090 to be purchased as part of a complete system. The goal was therefore not to find the cheapest standalone GPU, but to extract the best useful ComfyUI service node from the builder's mandatory bundle without paying for components that do not improve service capacity or latency.

One worker had already been built with the following independently selected specification:

Ryzen 9 9950X
MSI MAG X870E Tomahawk Max WiFi
Zotac RTX 5090 Solid OC 32 GB
T-Create Expert 64 GB DDR5-6000 CL34
2x Samsung 9100 Pro 2 TB RAID 0
Seasonic Vertex PX-1200 ATX 3.1 Platinum
Arctic Liquid Freezer III Pro 360
Fractal Design North XL

The second purchase introduced a RM30,999 promotion based on a Ryzen 7 9850X3D, Palit/Zotac RTX 5090, MSI PRO X870E-S EVO, G.Skill 64 GB, one Kioxia 1 TB SSD, Antec GSK1000, HydroShift 360 and O11 Vision. The promotion allowed component upgrades by paying the difference. This changed the answer from a simple standalone price-list optimization into a marginal-cost decision around a heavily discounted base.

Procurement update: source the spread, not necessarily the whole machine#

The component decision below remains valid, but the purchasing decision is no longer “buy every upgrade from IdealTech.” The RM38,647 quote is now the comparison ceiling. Obtain live, written quotes from the Malaysian distributors and authorised dealers and split the order only where the net saving survives tax, delivery, warranty and assembly costs.

Direct distributor purchasing is possible in principle, but “distributor price” is not normally a public one-unit consumer price. Distributors commonly require a reseller, system-integrator or corporate account, company documents, a minimum order, cash terms or recurring volume. They also avoid competing openly with the dealer channel that they supply. We should approach them truthfully as a company deploying its own AI infrastructure, offer cash payment and expected repeat purchases, and ask either for a corporate account or an introduction to their lowest-margin authorised dealer. We should not represent the company as a retailer if it is not one.

RTX 5090 channel#

Sun Cycle is the most relevant first contact because it distributes both Palit and Zotac, operates the local warranty portal, and publishes current SRPs. On 2026-09-22 its list showed:

GPU Published SRP
Palit RTX 5090 GameRock RM20,499
Palit RTX 5090 GameRock OC RM20,899
Zotac RTX 5090 Solid OC RM22,799
Zotac RTX 5090 Solid OC White RM23,299

These are SRPs, not confirmed dealer costs or offers to sell directly. Contact Sun Cycle sales on +60 10-392 7393 and request a live cash quote, available quantity, exact SKU, any attachment requirement and the warranty path. The target SKUs are NE75090019R5-GB2020G for the Palit GameRock and ZT-B50900J-10P for the Zotac Solid OC.

Standalone authorised-retailer supply is not impossible. Dotatech's RTX 50 collection advertised the Zotac Solid OC “from RM20,799” on the same date, although its individual product page showed a conflicting higher price. Dotatech appears on Zotac's Malaysia where-to-buy list, so it is worth requesting a written GPU-only quote rather than relying on either web price.

The IdealTech promotion nevertheless remains difficult to beat. The previously reconstructed list value of the base package was approximately RM35.2k, including a RM22,999 RTX 5090. Holding the other list values constant implies that the RM30,999 promotion values the bundled GPU at roughly RM18.8k. This is an approximation rather than an invoice allocation, but it means that finding a standalone 5090 at RM20.5k does not automatically save money: it gives up approximately RM4.2k of package discount. A full independent build only becomes compelling if the live 5090 quote approaches RM18.8k or distributor savings on the rest of the BOM more than offset the gap.

The claim that bundling exists solely to stop scalpers should not be treated as the complete explanation. There is no evidence here of a Malaysian law or universal NVIDIA rule requiring a full system. Scarce 5090 allocation, dealer-margin protection, warranty/fraud exposure and moving attached inventory can all produce the same retailer policy. The presence of at least one authorised GPU-only listing confirms that bundling is a channel policy, not an inherent product requirement.

The RTX 5090 itself remains non-negotiable for this workload. Its 32 GB VRAM and measured ComfyUI throughput are why the machine is being purchased; a 16 GB RTX 5080 is not an equivalent substitute merely because it is sold without a bundle.

Samsung SSD channel and the importance of live prices#

M-Link System's 17 March 2026 dealer list listed the Samsung 9100 Pro 2 TB (MZ-VAP2T0BW) at RM1,630 with a five-year warranty. That historical price would have made direct sourcing attractive. However, M-Link's 17 August 2026 list raised the same drive to RM2,592 and marked the 9100 Pro range as limited stock. This is the relevant recent comparison; the March price must not be used as a purchasing assumption.

The split-order calculation at the August published price is:

Line item Amount
IdealTech promotional base RM30,999
9950X upgrade +RM700
X870E Tomahawk Max upgrade +RM450
Seasonic PX-1200 upgrade +RM900
IdealTech subtotal, retaining the included Kioxia and declining both Samsung lines RM33,049
2x Samsung 9100 Pro 2 TB from M-Link at RM2,592 +RM5,184
Provisional split-order total RM38,233
All-IdealTech three-drive total RM38,647
Maximum saving before tax, freight and handling differences RM414

This table uses the current Seasonic quote. A confirmed Corsair or Lian Li substitution at the provisional list-price delta would reduce both compared totals by the same RM310 or RM620 respectively, so neither would change the RM414 SSD-sourcing spread.

RM414, or about 1.1%, is not enough to justify split invoicing and warranty handling unless the live M-Link quote improves. Any excluded tax or delivery charge could erase it. The arithmetic also gives a reusable rule: the two independently purchased drives together must cost less than RM5,598 to beat the IdealTech storage transaction at all. To justify the extra procurement path with at least RM1,000 saving, each drive should be RM2,299 or less, all-in. At RM2,592, buy the drives through IdealTech unless there is another material benefit.

M-Link explicitly publishes dealer prices, warranty contacts and an invitation to join as a reseller. Ask for a current September quote, whether the price includes every applicable tax, stock reserved for two matching units, delivery, five-year local warranty, and whether a corporate end-user or system-integrator account is acceptable. Samsung Malaysia states that SSD warranty service is carry-in to the point of purchase, so the invoice and authorised local channel matter.

Quote sequence and decision gates#

  1. Ask IdealTech for the base promotion plus the CPU and motherboard substitutions, no Samsung upgrade or add-on, and the included Kioxia retained. Request side-by-side installed-system prices for the regular Corsair HX1200i, Seasonic Vertex PX-1200 and Lian Li SX1200P; do not assume the standalone list-price differences will be honored inside the promotion.
  2. Ask M-Link for a same-day, all-in quote for two MZ-VAP2T0BW drives. Split the SSD purchase only at RM2,299 per drive or below; between RM2,300 and RM2,799, decide whether the small saving is worth separate warranty handling; at RM2,800 or above, use IdealTech.
  3. In parallel, ask Sun Cycle for a corporate/dealer cash quote for one Palit and one Zotac 5090, with no attached parts. Ask Dotatech and the other Zotac-authorised retailers for the same GPU-only quote.
  4. Price the complete independent BOM only if the best authorised 5090 quote is near RM18.8k, or if written distributor quotes on the remaining parts demonstrate enough additional saving to compensate.
  5. Compare final landed totals, not headline component prices. Require exact SKU, local authorised invoice, serial numbers, stock confirmation, DOA terms and warranty owner before placing an order.

This sourcing approach keeps the scarce 5090 bundle available as a fallback while testing the two realistic places to remove margin: a GPU bought through its actual distributor/dealer channel and high-markup add-ons bought from their specialist distributor.

Original component decision#

Buy the discounted RM30,999 promotional system, take the quoted CPU, motherboard and storage upgrades, select the 1200 W PSU under the price gate documented below, and add the original 1 TB Kioxia drive back as a third drive. Request the Zotac RTX 5090 rather than leaving the Palit/Zotac choice unspecified.

The final system is:

Component Selection Role
CPU AMD Ryzen 9 9950X Same CPU class as the existing worker; additional general-purpose headroom
GPU Zotac RTX 5090 Solid OC 32 GB Primary ComfyUI throughput component; request Zotac for fleet consistency
Cooler Lian Li HydroShift LCD 360 ARGB Included in the discounted package
Motherboard MSI MAG X870E Tomahawk Max WiFi Provides the two CPU-connected Gen5 x4 M.2 paths required by the model array
RAM G.Skill Trident Z5 64 GB DDR5-6000 Sufficient starting capacity; monitor production pressure before replacing it
Model cache 2x Samsung 9100 Pro 2 TB Linux mdadm RAID 0 on the two CPU-connected M.2 slots
System drive Kioxia Exceria Basic 1 TB Linux, containers, applications, downloads and outputs on a chipset M.2 slot
PSU 1200 W ATX 3.1 unit: Corsair HX1200i value default, Seasonic Vertex PX-1200 consistency option, or Lian Li SX1200P cost-first option under the gates below Headroom for the 575 W GPU without paying for unused 1500-1600 W capacity
Case Lian Li O11 Vision plus eight Antec Vision ARGB fans Fixed promotional-package selection
OS Linux The included unactivated Windows licence has no decision value for this worker

The price calculation is:

Line item Amount
Promotional base system RM30,999
Ryzen 7 9850X3D to Ryzen 9 9950X +RM700
MSI PRO X870E-S EVO to MAG X870E Tomahawk Max +RM450
Included Kioxia 1 TB to first Samsung 9100 Pro 2 TB +RM1,950
Antec GSK1000 to Seasonic Vertex PX-1200 +RM900
Second Samsung 9100 Pro 2 TB add-on +RM2,749
Quoted upgraded system RM37,748
Add the Kioxia Exceria Basic 1 TB back +RM899
Final three-drive system RM38,647

The seller should be asked to retain the Kioxia during the SSD upgrade if possible. The arithmetic still totals RM38,647 if IdealTech first credits its RM899 list price and then charges RM899 to add it back. Negotiating this duplicated transaction and obtaining all three PSU substitution quotes are the two reasonable remaining places to seek a small discount.

Why the promotional package changes the answer#

The initial comparison used the standalone component prices in the extracted IdealTech list. At those prices, the Ryzen 9 9950X, premium PSU and Samsung Gen5 drives appeared to be the obvious places to reduce cost.

The promotion changes the marginal economics. An indicative reconstruction of the base package from the same list is approximately RM35.2k before assembly, compared with its RM30,999 promotional price. The exact fan-pack accounting may differ, but the package clearly carries roughly RM4k or more of discount. The real discount is concentrated in the base configuration; most upgrade charges are ordinary retail price differences:

Upgrade Individual prices Difference Quoted charge
9850X3D to 9950X RM2,299 to RM2,999 RM700 RM700
PRO X870E-S EVO to X870E Tomahawk Max RM1,249 to RM1,699 RM450 RM450
Kioxia 1 TB to Samsung 9100 Pro 2 TB RM899 to RM2,849 RM1,950 RM1,950
Antec GSK1000 to Seasonic PX-1200 RM799 to RM1,700 RM901 RM900

This means it is advantageous to enter through the promotion, even if several base components are then upgraded.

The approximately comparable standalone build was RM41,482 without a separate OS drive. Adding the RM899 Kioxia would make it RM42,381. The RM38,647 promotional build therefore saves about RM3,734 while retaining the desired CPU, PSU and model-cache layout. The cases, coolers and RAM brands differ, so this is a practical system-level comparison rather than an identical bill of materials.

Workload and benchmark evidence#

The relevant workload is a ComfyUI service that changes large model sets. Warm inference is primarily a GPU problem, but cold requests also depend on how quickly approximately 42.47 GB of model and input files can traverse the complete storage, filesystem, container and model-loading path.

The storage investigation is documented in model-read-storage-layouts.md. Its benchmark protocol:

The important observed layouts were:

Storage layout Real model read Relevant conclusion
2x Crucial T710 Gen5 RAID 0 15.59 GiB/s Fastest confirmed path, on Threadripper with additional lanes
2x WD SN850X Gen4 RAID 0 on AM5 11.48 and 11.54 GiB/s Repeatable proof that two CPU-root-port drives on an X870/9950X-class host cross the target
2x Samsung 9100 Pro Gen5, effectively striped 11.54 GiB/s Direct evidence for the selected drive pair
1x Samsung 9100 Pro Gen5 5.93 GiB/s One high-end Gen5 drive did not cross the application target
4x visible SN850X RAID 0 3.49 GiB/s Visible drive count and synthetic claims do not prove that the application uses the fast path

The supporting captures are:

All observed hosts sustaining approximately 10 GiB/s or more on the real file set used two NVMe devices in parallel. No measured single-drive host crossed the threshold through the complete application path.

Storage decision and correction made during review#

An early recommendation proposed replacing the Samsung drives with two MSI Spatium M480 2 TB Gen4 drives. That would save RM2,700 at standalone prices, and two similar Gen4 SN850X drives had already demonstrated more than 11 GiB/s.

That recommendation was withdrawn after reviewing the storage postmortem. The M480 alternative is plausible but not proven:

The selected two-drive 9100 Pro configuration has direct supporting evidence and is the layout already recommended by the storage investigation. For a production purchase, the unvalidated saving is not worth giving up the best-supported route to the 10 GiB/s target.

A single 4 TB 9100 Pro was also rejected. It preserves capacity and avoids RAID 0, but the captured single-drive machine achieved only 5.93 GiB/s and added 21.31 seconds to the cold path. The two-drive array is deliberately a disposable cache, so redundancy is less valuable than model-switch latency.

Required physical storage topology#

The selected layout is:

Ryzen 9 9950X
├── PCIe 5.0 x16 ── Zotac RTX 5090
│
├── M2_1, CPU Gen5 x4 ── Samsung 9100 Pro 2 TB ─┐
│                                                ├─ mdadm RAID 0
├── M2_2, CPU Gen5 x4 ── Samsung 9100 Pro 2 TB ─┘  512 KiB chunks
│                                                   /srv/model-cache
│
├── M2_3, chipset Gen4 x4 ── Kioxia 1 TB
│                             Linux, Docker, application, downloads and outputs
└── M2_4, chipset Gen4 x4 ── available for future scratch/output storage

On the MAG X870E Tomahawk Max, M2_2 shares bandwidth with the rear USB4 controller. Configure M2_2 for full Gen5 x4 in BIOS and accept that the rear 40 Gbps USB-C ports will be disabled. This does not reduce the GPU's x16 link. The relevant lane-sharing details are in MSI's specification.

Use the following storage configuration:

Separating the OS is important. Container layers, logs, downloads and output writes must not contend with cold model reads on the striped volume. A failure of either Samsung drive destroys the RAID 0 array, so no irreplaceable data belongs there.

Why the motherboard upgrade stays#

The base MSI PRO X870E-S EVO provides one CPU-connected Gen5 x4 M.2 slot and two chipset-connected Gen4 x4 slots. See MSI's PRO X870E-S EVO specification.

It cannot reproduce the proven topology of two array members on independent CPU-connected M.2 paths. The RM450 Tomahawk upgrade is therefore functional, not cosmetic. It provides the required two Gen5 x4 CPU M.2 slots while retaining the RTX 5090 at Gen5 x16 and provides a chipset slot for the system drive.

Optional lane-expansion review: moving the OS drive to CPU-direct Gen5#

This question was reopened on 2026-09-23 to explore whether a motherboard or platform upgrade could move the OS drive from its chipset-connected Gen4 path to a third CPU-direct PCIe 5.0 x4 path without sacrificing any RTX 5090 bandwidth. This is an optional optimization, not a requirement of the selected build.

The selected build still has exactly three M.2 drives:

The exploration does not add a third cache member or a fourth drive. For the optional upgrade to count as a complete CPU-direct Gen5 solution:

No AM5 motherboard satisfies those upgrade conditions. The limitation comes from the AM5 CPU's lane budget, not from MSI's motherboard design. The correct present decision remains the Ryzen 9 9950X and X870E Tomahawk Max: both cache drives stay CPU-direct at Gen5 x4, the OS remains on the chipset at Gen4 x4, and the RTX 5090 retains Gen5 x16. Threadripper/TRX50 is the technically clean route to a third CPU-direct Gen5 M.2 path, but it is a platform migration rather than a sensible motherboard-only upgrade.

What running the RTX 5090 at x8 instead of x16 means#

The selected Zotac RTX 5090 Solid OC has a PCIe 5.0 x16 host interface. PCIe width describes the connection between the CPU and GPU:

Negotiated link Approximate theoretical bandwidth in each direction Change
PCIe 5.0 x16 63.0 GB/s baseline
PCIe 5.0 x8 31.5 GB/s 50% less host-link bandwidth

Changing to x8 does not disable CUDA cores, reduce the 32 GB VRAM capacity, or halve the GPU's internal GDDR7 bandwidth. A fully resident inference can therefore show little or no proportional slowdown. It does, however, halve the maximum bandwidth for CPU-to-GPU and GPU-to-CPU transfers. That path matters during model upload, CPU offload, tensors that spill beyond VRAM, pinned-memory transfers and workloads that stream data rather than leaving it resident.

The performance loss is workload-dependent rather than automatically 50%, but the link capability is unambiguously halved. This service is being built around a flagship 32 GB GPU and explicitly optimizes the cold model-loading path. Preserving x16 is therefore a hard acceptance condition; an x8 configuration is rejected even if a gaming benchmark or a warm, fully resident workflow happens to show a small difference.

Why the Ryzen 9 9950X cannot supply x16 plus three x4 paths#

AMD specifies 28 native lanes in total and 24 usable lanes for devices on the Ryzen 9 9950X. The remaining four form the chipset uplink. The 24 device lanes can be allocated as:

AM5 Ryzen 9 9950X device lanes
├── 16 lanes: PEG block, normally RTX 5090 at PCIe 5.0 x16
├──  4 lanes: dedicated CPU NVMe path
└──  4 lanes: general-purpose path used for a second NVMe or USB4

The Tomahawk makes the best allocation for this node:

RTX 5090       = x16
M2_1           = x4 CPU Gen5
M2_2           = x4 CPU Gen5, with rear USB4 disabled at full speed
Total          = 24 usable device lanes

The hypothetical all-CPU-direct layout would consume 16 + 4 + 4 + 4 = 28 device lanes before the chipset link: x16 for the GPU, x4 for each of the two Samsung RAID members, and x4 for the OS drive. A 24-lane AM5 CPU cannot provide that allocation. No BIOS update, X870E chipset, or premium VRM can create four missing CPU lanes.

The non-X3D Gigabyte X870E Aorus Elite WiFi7 exposes three physical CPU-connected Gen5 sockets by bifurcating the 16-lane PEG block. Its actual allocation is:

RTX 5090       = x8
M2A_CPU        = x4 from the dedicated NVMe path
M2B_CPU        = x4 taken from the PEG block
M2C_CPU        = x4 taken from the PEG block
USB4 controller = x4 from the remaining general-purpose path
Total          = 24 usable device lanes

Gigabyte explicitly states that populating either M2B_CPU or M2C_CPU makes PCIEX16 operate at no more than x8 in the official Aorus Elite specification. The board does not avoid GPU degradation; it exposes the user's choice between x16 graphics and the extra CPU M.2 paths. The same basic x8/x4/x4 trade applies to the other qualifying three-socket AM5 boards.

Audit of the IdealTech AM5 options#

Prices below are from the normalized IdealTech list dated 2026-09-22. Manufacturer lane tables, rather than the retailer's short descriptions, determine whether a board qualifies.

Motherboard IdealTech price CPU Gen5 M.2 implementation GPU result with all three M.2 paths used Decision
MSI MAG X870E Tomahawk Max WiFi RM1,699 Two onboard, independent of PEG x16 with two drives; no third path Retain
Gigabyte X870E Aorus Elite WiFi7, non-X3D RM1,839 Three onboard; M2B/M2C use PEG lanes x8 Reject
Gigabyte X870E Aorus Master, non-X3D RM2,799 Three onboard; M2B/M2C use PEG lanes x8 Reject
ASUS ROG Strix B850-E Gaming WiFi RM1,745 Three onboard; M.2_2/M.2_3 use PEG lanes x8 Reject
ASUS ROG Crosshair X870E Hero RM4,080 Three onboard through x8/x4/x4 bifurcation x8 Reject
MSI MEG X870E Godlike Max RM4,999 Two onboard plus bundled Gen5 M.2 XPANDER card x8 when the card uses CPU PCI_E2 Reject

The Aorus Master specification, ASUS B850-E specification, ASUS Crosshair Hero specification and MSI Godlike specification all disclose the relevant sharing or bifurcation. The Godlike can keep x16 while using its two onboard CPU M.2 sockets, but adding the third via its included XPANDER card occupies the second CPU PEG slot and changes the PEG allocation to x8/x8.

The retailer list also contains misleading socket counts. The Gigabyte Aorus Master X3D, Aorus Elite X3D Ice and Aero X3D Wood, ASUS X870E Dark Hero, and ASUS X870E-E Gaming WiFi7 Neo are described as having three Gen5 M.2 sockets in the short listing, but their current manufacturer specifications expose only two CPU Gen5 M.2 paths. They are not alternatives for this optional upgrade.

Whether to change the CPU and platform#

Changing to another AM5 CPU does not solve the problem. Ryzen 9000 and Ryzen 9000 X3D processors use the same AM5 I/O model; buying a 9950X3D-class part changes cores and cache, not the number of lanes available to this topology. Additional X870E chipset lanes are Gen4 lanes behind the shared chipset uplink and are not substitutes for another CPU-direct Gen5 path.

If the optional OS-path upgrade were pursued, the least-expensive lane-correct platform visible in the IdealTech list would be:

Component Selection IdealTech price Reason
CPU Ryzen Threadripper 9960X, pre-order RM7,399 92 total/88 usable CPU lanes, up to 80 at PCIe 5.0
Motherboard Gigabyte TRX50 AERO D RM3,099 Three onboard CPU-direct Gen5 x4 M.2 sockets and CPU Gen5 x16 GPU slots
Memory DDR5 ECC RDIMM Ask AM5 UDIMMs cannot be reused; four-channel RDIMM platform
Cooler sTR5-compatible full-IHS cooler From RM289 in the list The HydroShift AM5 cold plate/mount is not the Threadripper cooling solution
OS storage Gen5 x4 NVMe SSD, model to be selected Not yet quoted The selected Kioxia Exceria Basic is Gen4 and cannot satisfy an actual Gen5 OS-drive link

AMD's Threadripper 9960X specification lists 92 total and 88 usable lanes. AMD's Threadripper platform description states that TRX50 exposes up to 80 PCIe 5.0 lanes. The TRX50 AERO D specification confirms that M2A_CPU, M2B_CPU and M2C_CPU are each PCIe 5.0 x4, while both primary CPU expansion slots support PCIe 5.0 x16. This produces the optional target topology without bifurcating the GPU:

Threadripper 9960X / TRX50 AERO D
├── PCIEX16_1, CPU Gen5 x16 ── RTX 5090
├── M2A_CPU, CPU Gen5 x4 ───── Samsung 9100 Pro 2 TB ─┐
│                                                      ├─ RAID 0 model cache
├── M2B_CPU, CPU Gen5 x4 ───── Samsung 9100 Pro 2 TB ─┘
├── M2C_CPU, CPU Gen5 x4 ───── Gen5 OS SSD
└── M2D_CPU, CPU Gen4 x4 ───── available

The IdealTech description incorrectly summarizes the TRX50 AERO D as 4x Gen4 M.2; Gigabyte's primary specification shows three Gen5 plus one Gen4 socket, all CPU-connected. The board is 264 mm wide and fits within the O11 Vision's published E-ATX limit of 280 mm. The selected Zotac card is 329.7 mm long, below the case's 430 mm GPU limit. Physical fit is therefore plausible, though the builder must still validate radiator, cable and 3.5-slot GPU clearance in the complete assembly.

The CPU-and-motherboard subtotal changes from RM4,698 for the 9950X plus Tomahawk to RM10,498 for the 9960X plus TRX50 AERO D: RM5,800 more before RDIMM, cooler and any promotional-package effects. Threadripper also raises CPU TDP from 170 W to 350 W. The 1,200 W PSU, CPU cooler and sustained case thermals must be re-validated around a 575 W RTX 5090 rather than assumed adequate from connector wattage alone. IdealTech lists compatible RDIMMs as ASK, so a defensible final system total cannot yet be calculated. The quoted Kioxia Exceria Basic system drive is a PCIe 4.0 device. Moving it to M2C_CPU would make it CPU-direct, but it would still negotiate only Gen4 x4. Achieving an actual CPU-direct Gen5 OS link would therefore require a replacement Gen5 OS SSD as well as the Threadripper platform.

The ARCTIC Freezer 4U-M listed by IdealTech is explicitly sTR5-compatible and rated for processors up to 350 W, but cooler choice still needs a noise and sustained boost review. The existing workload averaged fewer than two CPU cores during cold loading, so Threadripper is not justified by present CPU utilization. Its value here is PCIe topology alone.

Final lane-expansion decision#

  1. Retain the Ryzen 9 9950X and X870E Tomahawk Max. It keeps the RTX 5090 at Gen5 x16, places both Samsung RAID members on independent CPU Gen5 x4 paths, and already exceeds the 10 GiB/s application target. The Kioxia OS drive remains on the chipset at Gen4 x4, as specified in the selected build.
  2. Do not replace the Tomahawk with the Aorus Elite, Aorus Master, ASUS B850-E, Crosshair Hero or MSI Godlike merely to obtain a third CPU M.2 socket. Every such AM5 path reduces the GPU to x8.
  3. Do not change to another AM5 CPU for lanes. It cannot change the platform lane budget.
  4. Do not migrate to Threadripper solely to accelerate the OS drive without measured evidence of an OS bottleneck. The known application bottleneck is the model cache, and that already has two independent CPU-direct Gen5 paths. Threadripper remains a future option only if a measured workload justifies its RM5,800 CPU-and-board premium plus new RDIMM, cooling and Gen5 OS storage.

If a future Threadripper build is evaluated, its topology test should simultaneously show the RTX 5090 at 32.0 GT/s x16, both Samsung RAID members at 32.0 GT/s x4, and the replacement Gen5 OS SSD at 32.0 GT/s x4. It should also confirm that all three NVMe devices enumerate beneath CPU root ports rather than the chipset. An x8 GPU result remains unacceptable regardless of synthetic SSD throughput.

CPU decision#

The Ryzen 7 9850X3D included in the package is already an 8-core/16-thread Zen 5 CPU with a 5.6 GHz boost clock and 120 W default TDP. It is sufficient for the measured workload. Resource traces from the cold model-loading captures averaged fewer than two process CPU cores, while warm execution averaged about 1.16 cores. The 5090 determines most resident throughput.

The Ryzen 9 9950X upgrade therefore is not required for the current ComfyUI benchmark. It was retained because:

For a strictly minimum-cost worker, retaining the 9850X3D remains technically reasonable. The final choice favors operational headroom and fleet consistency over the last RM700 of savings. AMD's published 9850X3D specification is available here.

PSU, incoming-power and UPS decision#

Decision summary#

The complete evidence, same-tier comparison, limitations, site-power plan, and procurement decision tree are maintained in the dedicated power-supply and site-power decision.

Why 1200 W is the balanced capacity#

The selected Zotac RTX 5090 Solid OC is specified at 575 W and recommends a 1000 W system PSU. NVIDIA's own RTX 5090 specification also gives 575 W total graphics power and a 1000 W system recommendation based on a Ryzen 9 9950X host. The included Antec GSK1000 therefore meets the published requirement, but it is the floor rather than a generous continuous-service design point.

The real ComfyUI captures averaged fewer than two CPU cores during cold loading, so this worker normally will not combine a 575 W GPU load with maximum CPU package power. Nevertheless, the system also contains the pump, fans, motherboard, memory and three NVMe drives, and future preprocessing could raise concurrent CPU use. Moving from 1000 W to 1200 W gives 20% more nominal capacity, lower sustained loading and useful thermal/aging margin without the waste of a 1600 W unit. A larger PSU does not make the computer draw its nameplate wattage, but capacity beyond 1200 W provides no throughput or meaningful additional protection for this parts list.

PSU model comparison and price gate#

The prices are from the IdealTech list dated 2026-09-22. The provisional system totals below apply the list-price difference from the included RM799 Antec GSK1000; IdealTech must confirm the actual promotional substitution price before the total is changed.

PSU List price / provisional package surcharge Relevant evidence Decision
Antec GSK1000, 1000 W Gold RM799 / included ATX 3.1, native 12V-2x6, ten-year warranty; passed Cybenetics power-excursion and ripple tests Adequate minimum, but no capacity above Zotac's 1000 W recommendation
Antec GSK1200, 1200 W Gold RM999 / +RM200, marked COMING ATX 3.1, two native 12V-2x6 cables, ten-year warranty; independently tested Good low-cost fallback only after stock and exact warranty are confirmed
Lian Li SX1200P, 1200 W Platinum RM1,079 / +RM280 ATX 3.1, native 12V-2x6, ten-year warranty, 0-50 °C full-load rating; Cybenetics measured 31.51 mV 12 V ripple and 20.4 ms hold-up Best price/performance candidate
Corsair HX1200i, 1200 W Platinum RM1,389 / provisional +RM590 ATX 3.1, included 12V-2x6, ten-year warranty; measured 23.41 mV ripple, 21.8 ms hold-up, and lower average noise than the tested Vertex Balanced new-node default if it saves at least RM250 all-in
ASUS ROG Strix 1200P, 1200 W Platinum RM1,539 / provisional +RM740 ATX 3.1, native 12V-2x6 and ten-year warranty; capable independent result but high measured 230 V inrush No material gain over the cheaper Corsair
Corsair HX1500i, 1500 W Platinum RM1,579 / provisional +RM780 ATX 3.1, included 12V-2x6 and ten-year warranty; excellent ripple but more capacity than this node can use Good hardware, weaker system value than HX1200i
Seasonic Vertex PX-1200, 1200 W Platinum RM1,700 / quoted +RM900 Current ATX 3.1 revision, native 12V-2x6 and twelve-year warranty; Cybenetics measured 23.50 mV 12 V ripple and 25.0 ms hold-up on an earlier ATX 3.0 revision Keep if owned; use for the new node if Corsair saves less than RM250
Seasonic Prime TX-1600 Noctua, 1600 W Titanium RM1,999 / provisional +RM1,200 ATX 3.1, native 12V-2x6, twelve-year warranty, premium efficiency and acoustics Reject: RM610 above HX1200i for unused capacity and silence

Cybenetics' 230 V testing confirms that the Antec GSK1000, Antec GSK1200, Lian Li SX1200P, Corsair HX1200i and Seasonic Vertex PX-1200 all operate within their tested limits. The Corsair sample was quieter, regulated 12 V more tightly, and had essentially the same full-load 12 V ripple as the tested Vertex; the Vertex held output longer after AC loss and carries two more years of warranty. These are small trade-offs, not evidence of a reliability gulf. The Lian Li is noisier and has higher ripple, but its results remain comfortably suitable for this system. None is a mains conditioner.

At the list-price deltas, the Corsair would produce a provisional RM38,337 total and the Lian Li approximately RM38,027, compared with the quoted RM38,647 Seasonic ceiling. Request all three prices, but do not delay the node or accept an ambiguous SKU, warranty, or cable revision. The current ceiling remains in force until the builder supplies written substitution quotes.

What a PSU can and cannot protect#

The Seasonic, Corsair, Lian Li and Antec models all provide the normal internal protection classes: over-current, over-voltage, under-voltage, short-circuit, over-power and over-temperature shutdown. These protect the PSU and downstream components when the PSU output or load becomes abnormal. Better ripple control, transient response and hold-up time can improve operating margin, but the difference is measured in milliseconds and does not bridge a grid outage.

Protection is layered because no single device covers every failure mode:

Failure mode Primary control What it does not solve
PSU overload, output fault or overheating Quality ATX 3.1 PSU protections Utility outage, building wiring fault or direct/high-energy surge
Branch-circuit overload and earth leakage Correct breaker plus RCD/RCBO, installed and tested by a licensed electrician Ride-through or application shutdown
Lightning/switching transient entering the installation Properly earthed switchboard SPD, with coordinated point-of-use protection where required Sustained outage or bad earthing
Routine undervoltage/overvoltage and short interruption Correctly sized line-interactive UPS with AVR and pure-sine output Long outage beyond battery runtime
Severe or persistently dirty supply Online double-conversion UPS after measurement confirms the problem Long-duration backup without a generator or large battery system

Malaysian residential electrical arrangement#

Malaysia's Energy Commission specifies 230 V single-phase and 400 V three-phase low-voltage supply, with normal steady-state tolerance of +10%/-6%. TNB describes domestic service as either single-phase two-wire or three-phase four-wire; “two-phase residential supply” is not the normal service classification. If the plan means using two separate phases from a three-phase board, each workstation must still be connected phase-to-neutral at approximately 230 V. It must never be connected phase-to-phase at approximately 400 V.

The two dedicated home runs from the main distribution board are a good reliability choice because a fault or overload on another appliance circuit is less likely to trip a worker. Have a Malaysian licensed electrical contractor design, install and test them rather than specifying breaker or conductor sizes from the server BOM. Dedicated branches do not condition utility power: both machines still share the premises' incoming service, distribution board, neutral and earthing system. The acceptance scope should include:

If the premises later changes to three-phase service, keep each computer as a 230 V single-phase load and place the two dedicated circuits on different phases after the electrician balances the whole property. The phase migration does not require changing the PC PSUs. It may improve fault isolation and whole-site capacity, but it does not eliminate the need for earthing, residual-current protection or surge protection. TNB's published minimum supply scheme allows up to 12 kVA on a 230 V single-phase service. The two workers alone are not a reason to buy a three-phase upgrade; make that decision from measured whole-premises maximum demand, cooling load, planned worker count and the electrician's/TNB's assessment.

Relevant primary guidance is the Energy Commission's residential wiring guide and TNB's supply description.

UPS decision and economic gate#

A UPS would provide two useful capabilities: AVR for supply outside its preferred pass-through band, and battery time to ride through a short interruption or shut Linux down cleanly. It is not required merely because the utility remains within Malaysia's declared supply tolerance: all shortlisted PSUs are universal input designs that include the local 230/240 V nominal service. Site logging must still confirm the actual voltage behavior. A switchboard SPD and correct earth are also more direct protections against incoming transients than paying more for a PC PSU.

Do not use a common 1500 VA/900 W desktop UPS for this machine. Its watt rating can be lower than the worker's possible input demand even though its VA number looks large. A suitable per-machine starting class is approximately 2200 VA with at least 1800 W continuous output, pure-sine output, AVR, USB or network shutdown support, and user-replaceable batteries. The Eaton 5PX 2200i G2 is a concrete reference: 2200 VA/2200 W, line-interactive, pure sine wave, automatic shutdown support, 98% stated full-load efficiency and ten minutes of stated runtime at half load. M-Link's 19 August 2026 dealer promotion listed it at RM3,790.

Two such UPS units would cost RM7,580, about 9.8% of the two RM38,647 workers, before replacement batteries and conversion losses. Amortized over five years, the purchase price alone is approximately RM126 per month for the pair. Sealed lead-acid batteries normally require replacement in roughly three to five years, and APC notes that every 8 °C increase above 25 °C can approximately halve expected battery life. This matters in a warm equipment room.

For this bootstrapped deployment, the recommended sequence is:

  1. Install the dedicated protected circuits, switchboard SPD and power-quality logging now.
  2. Make the OS/configuration reproducible, keep application state backed up off-machine, and make customer jobs retryable. The RAID 0 model volume is already disposable.
  3. Record at least 30 days of voltage and outage data, including storms, and record the recovery time and lost gross margin from every interruption.
  4. Buy UPS capacity when the expected monthly loss from interruptions exceeds its monthly ownership cost, or when paying-customer commitments make graceful shutdown a baseline requirement.
  5. If purchasing, prefer one properly sized UPS per machine for fault isolation. Also protect the ONT, router and switch; server runtime has no service value if the network path is dead. Configure automatic job draining and shutdown rather than treating the UPS as long-duration generation.

A single central 5 kVA online UPS may look cheaper than two premium tower units, but it adds a shared failure point, continuous conversion loss, fan noise, special distribution and more complex maintenance. Revisit that architecture only after the deployment becomes a real equipment room with three or more workers or a generator. Online double conversion is not the 80/20 choice unless logging shows persistent out-of-tolerance voltage or frequency that line-interactive AVR cannot handle.

RAM decision#

Keep the included 64 GB kit. A 64 GB host completed the benchmark workflow, and warm inference does not benefit simply from unused system memory. The extracted list priced the available 128 GB kit at RM8,999, approximately RM4,000 more than the 64 GB kits. That is poor value without evidence of production memory pressure.

Monitor process RSS, swap activity, major faults and cache eviction in production. If real workloads regularly exceed available memory or CPU model offload becomes common, replace the two-DIMM kit with a validated 2x64 GB kit. Do not assume adding a second 2x32 GB kit will retain DDR5-6000 stability.

GPU decision#

The RTX 5090 and its 32 GB VRAM are the non-negotiable performance component. At standalone prices, a Gigabyte Windforce OC was RM700 cheaper than the Zotac and would have been a reasonable equivalent GPU class. The promotion instead supplies Palit or Zotac.

Request the Zotac explicitly because the existing worker uses it. Identical GPU models simplify power, thermal and failure comparisons between the two nodes. If IdealTech will not guarantee the brand, either 5090 should execute the workload, but the quote and acceptance record must identify the exact supplied SKU.

Cooler, case and airflow decision#

The HydroShift LCD and O11 Vision are not the independently selected price/performance choices; they are part of the discounted package, and replacing them would erode the package value.

The O11 Vision supports a side-mounted 360 mm radiator. Lian Li lists the HydroShift as supported in this position but notes that its performance is less optimal than a top mount. See the HydroShift compatibility guidance and O11 Vision layout.

Ask the builder to follow the supported side orientation and use an airflow plan equivalent to:

The builder must verify sustained NVMe temperatures because the storage target depends on avoiding Gen5 thermal throttling, not merely on keeping the CPU cool.

Alternatives considered#

Cost-reduced promotional build: RM36,947#

This version would keep the 9850X3D and Antec GSK1000, upgrade only the motherboard for RM450, retain the Kioxia, and add two Samsung drives at RM2,749 each:

RM30,999 + RM450 + RM2,749 + RM2,749 = RM36,947

It is technically sound and RM1,700 cheaper than the Seasonic-based ceiling, RM1,390 cheaper than the provisional Corsair alternative, or RM1,080 cheaper than the provisional Lian Li alternative. It was not selected because the 9950X has broader capability and a 1200 W PSU provides useful continuous-service power margin.

Two MSI M480 2 TB drives#

This was the leading standalone price/performance alternative. It was rejected because it has no application-level validation in the captured dataset. It may be revisited only if the exact physical layout passes the same model-read acceptance test before the return window closes.

One 4 TB Samsung 9100 Pro#

Rejected because the observed single-drive application path delivered 5.93 GiB/s and a 21.31-second cold penalty. Nominal sequential read speed was not enough.

Upgrade to 128 GB immediately#

Rejected because it costs approximately RM4,000 more, 64 GB completes the workload, and there is no production memory-pressure evidence yet.

Retain the base motherboard#

Rejected because it has only one CPU-connected Gen5 M.2 slot. Placing the second model drive behind the chipset would depart from the closest proven AM5 storage topology to save only RM450.

Retain the base CPU and PSU#

Technically acceptable and the best minimum-cost choice. Retaining both saves RM1,600 against the current Seasonic-based quote or RM980 against the provisional Lian Li alternative. It was not selected because the CPU has operational value beyond the current benchmark and the move from the minimum 1000 W PSU to 1200 W adds useful continuous-service margin.

Instructions to put on the IdealTech order#

  1. Supply the Zotac RTX 5090 SKU if available; record the exact SKU on the invoice.
  2. Retain or add back the included Kioxia Exceria Basic 1 TB as a third drive.
  3. Install the Samsung drives in M2_1 and M2_2, not in chipset slots.
  4. Install the Kioxia in M2_3 and use it as the system drive.
  5. Configure M2_2 for full Gen5 x4; disabling rear USB4 is intentional.
  6. Confirm the RTX 5090 still negotiates its full intended x16 link.
  7. Record the exact PSU model and revision. Use only that PSU's supplied direct 12V-2x6 GPU cable, fully seated, without the multi-8-pin adapter where possible; never reuse modular cables from a different PSU model.
  8. Install both Samsung motherboard heat spreaders and ensure direct case airflow reaches them.
  9. Configure the O11 Vision fans for bottom/side intake and rear exhaust.
  10. Do not place the operating system or irreplaceable output data on the RAID 0 model cache.

Acceptance test before treating the node as production-ready#

The parts list alone does not prove the desired model-loading performance. Validate the completed machine in this order:

  1. PCIe topology
    • Both 9100 Pros negotiate 32.0 GT/s at x4.
    • The RTX 5090 negotiates its intended x16 width under load.
    • The Kioxia is on a chipset path.
  2. Array
    • mdadm reports two healthy RAID 0 members, 512 KiB chunks and approximately 4 TB usable capacity.
    • Physical member read counters increase approximately equally during a large read.
  3. Synthetic floor
    • Direct 1 MiB QD32 sequential reads comfortably exceed 20 GB/s.
    • Cache-evicted buffered single-stream reads exceed approximately 12 GB/s.
  4. Application storage
    • Run the benchmark's normal buffered model-file reader after cache eviction.
    • Require at least 10 GiB/s in repeated samples, not merely in the best sample.
  5. End to end
    • Run five verified cold/warm ComfyUI pairs.
    • Every cold run must physically read the resolved model set.
    • Every warm run must record zero physical model reads.
    • Target a 5-8 second median cold-to-warm penalty for the current workflow.
  6. Thermals
    • Read at least 200 GB continuously while recording both NVMe temperatures and link states.
    • Reject or correct a configuration that briefly passes before thermal throttling below the target.
  7. Electrical and PSU
    • Record idle, sustained ComfyUI and combined CPU/GPU stress input power at the branch meter.
    • Confirm the dedicated circuit remains stable without abnormal plug/connector heating, nuisance trips or material voltage sag; have the electrician correct the installation rather than increasing breaker size ad hoc.
    • After initial thermal cycling, shut down and isolate mains power before visually checking the native 12V-2x6 connection for full insertion, discoloration or deformation. Follow the PSU and GPU makers' cable-bend guidance; do not repeatedly disconnect a healthy connector without cause.
    • If a UPS is later installed, test its self-test, monitoring and automated job-drain/shutdown path under controlled conditions before relying on its advertised runtime.

The already-built first worker should be subjected to the same test. If it misses the target, fix its M.2 placement, M2_2/USB4 BIOS setting, RAID/filesystem placement or cooling before changing the second worker's component selection.

Boundaries of this decision#