VoltgridNews

Dell Pro Max Micro Specs: 24GB RTX PRO 4000 Runs 8B at 52 tok/s, Not 27B

StorageReview measured 52.0 tok/s on Ministral 3 8B from the 2.9-litre box's 70 W card, but Qwen3.8 27B did not fit in 24 GB. Dell.com lists it from $1,449, plus $3,870 for the GPU.

Local AI Desk

6 min read

Dell Pro Max Micro FCM2250 2.9-litre desktop seen from the front, with power button, USB ports and Dell logo

The Dell Pro Max Micro (FCM2250), the 2.9-litre desktop StorageReview tested.

Image: Dell

Source · Press image from the Dell product page, used for news reporting.

Dell's Pro Max Micro, a 2.9-litre desktop, served Ministral 3 8B at 52.0 tokens per second for one request on its 70 W, 24 GB NVIDIA RTX PRO 4000 SFF card, StorageReview measured in a review published Nov. 15, 2026.

The same tests found the ceiling as clearly as the speed. Qwen3.8 27B, which StorageReview said needs 30 GB of GPU-usable memory at Q4_K_M for its weights and one request's key-value cache, did not load on the card's 23.9 GB of usable memory. Dell's US configurator, read on Nov. 16, 2026, starts the Micro (model FCM2250) at $1,449.00 and charges $3,870.00 more for the RTX PRO 4000. Voltgrid found no other independent lab's measurements of the machine as of Nov. 16, 2026, so this is a product file, not a review.

What it is

The Micro is the smallest workstation in Dell's Pro Max desktop line. StorageReview's unit paired a 24-core Intel Core Ultra 9 285 with the RTX PRO 4000 Blackwell SFF Edition, 96 GB of DDR5-6400 system memory on two CSODIMM modules and two 1 TB PCIe Gen5 drives. The chassis measures 206 x 79.3 x 178 mm, and power comes from an external 280 W adapter; Dell's configurator also lists a 180 W one.

StorageReview reports that Dell runs the 65 W Core Ultra processors at 85 W in this chassis; Dell's configurator lists the parts at 65 W. The 24 GB card is the largest graphics option Dell offers in the Micro, according to StorageReview. That one fact sets what the box can do for local language models: everything a model needs while it answers, its weights plus the key-value cache that grows with each request's context, has to sit in those 24 GB to run at the card's speed.

StorageReview put the tested build, with a three-year ProSupport contract, Wi-Fi 7 and 5 Gb Ethernet, at $11,999 on Dell.com. That is three times the price of the Corsair FlexPrime V20C and the AMD Ryzen AI Halo it was tested against, the lab noted.

What it runs, and what it does not

On the llama.cpp server with CUDA, 4,096-token prompts and 1,024-token answers, the Micro served the smaller Ministral 3 3B at 80.7 tokens per second for one request and 201.5 across four. Ministral 3 8B ran at 52.0 for one request and 108.9 across four, with the first token after 1,477 milliseconds. StorageReview ran Ubuntu 26.04.1 with NVIDIA driver 595.99.02. It did not state the quantization of the Ministral models, so those figures cannot be set against runs elsewhere at a known precision.

The 20B class fits. In Ollama 0.40.3, gpt-oss:20b drove a coding agent with a 64K context at 76.2 tokens per second, though the agent passed only one of its three runs; StorageReview said pass counts on that model vary between runs and treated the generation rate as the hardware result. A retrieval test that answered questions with Phi-4-mini generated 137.0 tokens per second.

Above that, the card runs out. Besides Qwen3.8 27B, StorageReview listed gpt-oss-120b, which needs 90 GB, and the 129.3 GB MiniMax M2.7 as models the Micro could not hold, and Qwen-Image 20B did not load for image generation. The lab's own summary: 24 GB covers serving up to roughly the 20B class at 4-bit quantization.

The small box has a thermal cost on the processor side. The Core Ultra 9 285 peaked between 98 and 105 degrees C in every all-core test and trailed a tower with the same core layout by 17 to 26 percent in compression, rendering and encoding. The graphics card peaked at 73 C during language-model serving. StorageReview did not report wall power or fan noise.

Why 24 GB stops a 27B model

A language model answers by reading its weights and a growing key-value cache from fast memory, so both have to fit in the card's own memory to run at the card's speed. Q4_K_M is a 4-bit-class quantization that shrinks the weights, yet StorageReview said Qwen3.8 27B still needs 30 GB at that setting for its weights and one request's cache.

NVIDIA lists the RTX PRO 4000 Blackwell SFF Edition at 24 GB, and the lab measured 23.9 GB usable, so the model did not load, though the 32 GB Arc Pro B70 and both 128 GB machines ran it. For buyers that makes memory the first spec to size against.

How it compares

StorageReview ran the same suite on four other machines. On Ministral 3 8B at one request, the Micro's 52.0 tokens per second trailed the $3,999.99 Corsair FlexPrime V20C, whose 32 GB Intel Arc Pro B70 reached 63.7, and led the Dell Pro Max with GB10 at 37.0 and the AMD Ryzen AI Halo at 30.6. At four requests the order held: 141.8 on the V20C, 108.9 on the Micro, 97.2 on the GB10 and 66.6 on the Halo. Dell's Pro Precision 9 T2 tower, with a 96 GB RTX PRO 6000 Max-Q, ran 167.3 and 384.9.

On StorageReview's suite the 24 GB Micro served Ministral 3 8B at 52.0 tok/s, behind the 32 GB V20C's 63.7; quantization not stated.

Graphic: Voltgrid News

The software paths differ, and StorageReview said so. The Micro, the T2 and the GB10 ran llama.cpp on CUDA, the V20C on Intel's SYCL backend and the Halo on AMD's ROCm. The GB10 and the Halo also ran on their makers' own Linux images rather than the Ubuntu release the other three shared. The quantization for this model is not stated for any of the five machines.

The two 128 GB machines are slower on this small model, but they hold far larger ones. The Dell GB10 box and the Ryzen AI Halo each carry 128 GB of memory shared between processor and graphics, at a reported 273 GB/s and AMD's stated 256 GB/s, against Intel's 608 GB/s launch figure for the V20C's Arc card, as StorageReview cites it, and NVIDIA's 432 GB/s for the Micro's own 24 GB card. Both ran Qwen3.8 27B at Q4_K_M, at 11.2 and 9.1 tokens per second for one request, where the Micro could not load it, and the V20C ran it at 19.8. Dell.com lists the 128 GB Dell Pro Precision with GB10, which StorageReview tested as the Dell Pro Max with GB10, at $7,901.00 with a 2 TB drive (read Nov. 16, 2026), as covered in our review of the Dell Pro Precision with GB10; StorageReview listed the Halo at $3,999 with a 2 TB drive in its July review and said on Nov. 15 that Micro Center charges $3,999.99, as in our Ryzen AI Halo review.

Where the Micro pulls ahead is in the Ollama and image tests, which ran on CUDA on the NVIDIA machines, on ROCm on the Halo and on Vulkan on the Arc card. Its 76.2 tokens per second on the gpt-oss:20b agent test beat the GB10's 53.9, the Halo's 41.2 and the V20C's 32.2, and it generated 11.46 FLUX.2 klein 4B images per minute at Q4_0 in stable-diffusion.cpp, against 9.96 on the GB10. StorageReview said the Arc card's Vulkan path accounts for much of the Micro's lead over the V20C in those tests. Readers weighing the 32 GB alternative will find its measurements in our Corsair FlexPrime V20C product file, and the step up to several 96 GB cards in our file on the Pro Precision 9 T4.

Who it suits, on the numbers so far

For a team that wants a CUDA machine on a desk or behind a monitor, serving 8B to 20B models to a few users, the measured rates are workable in 2.9 litres, and StorageReview pointed to the commercial package of certified RTX PRO graphics, vPro Enterprise and on-site support as what the price buys. For anyone planning on 27B models or larger, the 24 GB card is a hard stop, and Dell sells no larger card for this chassis. For about a third of the tested build's price, the 32 GB V20C ran the 8B model faster in the same suite and also loaded the 27B model.

What is not known yet

One lab has measured the Micro. The quantization of its llama.cpp runs, its power draw at the wall and its noise under load are unreported, and Voltgrid found no second outlet with language-model results as of Nov. 16, 2026. Prices here are Dell.com's US list on Nov. 16, 2026; Voltgrid found no street price for configurations with the RTX PRO 4000 as of that date. A second independent measurement, with the quantization stated, is the next thing to watch for.

How it compares

Full table
Dell Pro Max Micro Specs: 24GB RTX PRO 4000 Runs 8B at 52 tok/s, Not 27B: how the machine compares with other local AI hardware
ProductMemoryBandwidthAI computeMeasured speedPrice
ASUS ExpertCenter Pro ET900N G3ASUS (NVIDIA DGX Station GB300 platform)748 GB coherent: 252 GB HBM3e (GPU) + 496 GB LPDDR5X (CPU)[1]7.1 TB/s (GPU HBM3e); 396 GB/s (CPU LPDDR5X)[1]up to 20 PFLOPS AI performance (ASUS gives no precision or sparsity label) (sparse)[2]GPT-OSS-120B MXFP4, vLLM, 512/512, 1-128 streams: 9,280 aggregate output tok/s at 128 streams; 5,023 on 8,192/1,024 (StorageReview, ASUS-supplied unit, no add-in GPU)[3]$111,999.99 at Central Computers, US (ET900N G3-2SSD-V2, read Nov 8, 2026); no ASUS list price[4]
HP ZGX Fury AI StationHP252 GB HBM3e GPU + 496 GB LPDDR5x CPU (4x 128 GB SOCAMM); 748 GB unified[5]7.1 TB/s (GPU HBM3e); 396 GB/s (CPU LPDDR5x)[5]up to 20 petaFLOPS FP4 (HP gives no sparsity label) (sparse)[5]Two-unit cluster with an ASUS ET900N G3 over two 400G DACs: GLM-5.3 NVFP4 5,018 output tok/s at 256 streams, 512/512, vLLM 0.27.1 TP2 with MTP (StorageReview); no single-unit HP result[6]$132,000.00 on HP Store US (ZGX Fury G1n, 3-yr warranty, no graphics card, 4x 2 TB SED SSDs; Add to cart; read Nov 11, 2026)[7]
MSI XpertStation WS300MSI (NVIDIA DGX Station platform)252 GB HBM3e GPU + 496 GB LPDDR5X CPU (748 GB coherent)[8]7.1 TB/s (GPU HBM3e); 396 GB/s CPU LPDDR5X[8]—StorageReview vLLM: gpt-oss-120b MXFP4 9,294 output tok/s at 128 streams (512/512), 5,038 on 8,192/1,024; MiniMax M3 NVFP4 1,041 at 32 streams with EAGLE3-GQA at a forced acceptance length of 3 (best-case)[8]$99,999.00 'Start From' at Newegg US (model WS300T60L, 2x 2 TB NVMe RAID1), request-a-quote listing sold by Newegg (read Nov 15, 2026)[9]
NVIDIA DGX StationNVIDIA (systems built by ASUS, Dell, GIGABYTE, HP, MSI, Supermicro and Exxact)748 GB coherent: 252 GB HBM3e (GPU) + 496 GB LPDDR5X (CPU)[10]GPU HBM3e 7.1 TB/s; CPU LPDDR5X 396 GB/s; NVLink-C2C 900 GB/s between them[10]15 PFLOPS FP4 (without sparsity)[10]gpt-oss-120b MXFP4, vLLM, 512/512 chat workload: 9,280 output tok/s at 128 streams (MSI WS300 9,294), single GB300 (StorageReview, ASUS ExpertCenter Pro ET900N G3)[3]No NVIDIA list price; lowest US partner listing read Nov 4, 2026: Exxact Valence VWS-158270643 from $98,450 (Tom's Hardware found $94,930 in Aug); Dell Pro Precision with GB300 lists $160,195[11]
Supermicro Super AI Station (ARS-511GD-NB-LCC)Supermicro (NVIDIA DGX Station platform)748 GB total coherent: 252 GB HBM3e GPU + 496 GB LPDDR5X system[12]7.1 TB/s (GPU HBM3E); 396 GB/s (CPU LPDDR5X)[13]up to 20 PFLOPS FP4 (Supermicro gives no sparsity label; ServeTheHome describes it as sparse FP4)[12]Qwen3.8 Flash Next NVFP4, vLLM, tool-loop 4,096-in/512-out: several scenarios exceeded 3,000 output tok/s at 32 concurrent users, still rising (ServeTheHome; RTX PRO 2000 installed)[14]$92,887.47 before tax and shipping on Supermicro's online store (ARS-511GD-NB-LCC-01-G2); about $90,101.05 with a 3% new-customer discount (TechRadar, Sep 1, 2026)[15]
NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA (sold through PNY, TD SYNNEX and workstation makers)96 GB[16]1,792 GB/s[16]4,000 AI TOPS (FP4, with sparsity) (sparse)[16]gpt-oss-120b MXFP4, stock vLLM, 512/512 chat workload: 3,064 output tok/s at 128 streams (1,169 on 8,192/1,024 prompts); Server Edition at 600W (StorageReview)[17]$16,000 on NVIDIA's US marketplace (Workstation Edition), listed out of stock[18]
Apple Mac Studio (M5 Ultra)Appleup to 512 GB unified (96 GB on 30-core M5 Ultra; 256 GB or 512 GB on 36-core/80-core M5 Ultra)[19]1.2 TB/s[19]—GLM-5.3-Flash MLX 4-bit with MTP on TensorFold, ISL 2048/OSL 512: 94.0 tok/s at 0 context, 96.5 at 128K, 79.4 at 512K; TTFT 1.1 s at 0, 66.3 s at 128K (Tom's Hardware, 256 GB M5 Ultra)[20]$22,299 minimum with 512 GB ($6,799 36-core CPU/80-core GPU M5 Ultra config plus $15,500 memory upgrade; Oct 28, 2026)[21]
Corsair FlexPrime V20C Workstation (CSW-9040004-NA)Corsair32 GB GDDR6 on the Arc Pro B70 GPU + 32 GB (2x 16 GB) DDR5 system memory[22]608 GB/s (GPU GDDR6)[22]—Qwen3.8 27B Q4_K_M, llama.cpp server: 19.8 tok/s at 1 request, 33.5 at 4, 35.4 at 8; TTFT 9,005 ms on 8,192-token prompt (StorageReview)[23]$3,999.99 on Corsair US store (32 GB DDR5, 1 TB SSD; read Nov 15, 2026)[22]
Show the other 32 machines
Dell Pro Max Micro Specs: 24GB RTX PRO 4000 Runs 8B at 52 tok/s, Not 27B: how the machine compares with other local AI hardware: the other machines
ProductMemoryBandwidthAI computeMeasured speedPrice
NVIDIA RTX Spark (N1X) PCsNVIDIA (MediaTek collaborated on the custom CPU design)Up to 128 GB LPDDR5X (20-core CPU / 6,144-core GPU version); up to 64 GB (18-core / 5,120-core laptop version)[24]Up to 300 GB/s: LPDDR5X-9400 on a 256-bit bus (NVIDIA's product page lists no bandwidth)[25]—gpt-oss:20b via Ollama in a Codex CLI coding agent, 64K context: 58.5 tok/s generation, 3 of 4 tasks passed (Dell XPS 16, 20-core N1X, 64 GB; StorageReview)[26]Laptops from $2,599; pricing and configurations vary by region[27]
AMD Ryzen AI Halo (Ryzen AI Max+ PRO 495, 192 GB)AMD192 GB LPDDR5X (256-bit)[28]273 GB/s[28]——$7,299.99 for the Linux version (released the week of Oct 12, 2026); Windows version coming soon[28]
ASUS Ascent GX10ASUS64 GB or 128 GB LPDDR5X-8533 unified[29]273 GB/s (8533 MT/s), as listed by StorageReview; ASUS's spec page states no bandwidth[30]Up to 1 PFLOP FP4 (GB10; NVIDIA's footnote: theoretical, using the sparsity feature). ASUS's pages say 1 petaFLOP / FP4 with no sparsity label (sparse)[31]gpt-oss-120b, vLLM online serving, equal ISL/OSL: 70 tok/s at batch 1 rising to 680 tok/s aggregate at batch 64 (StorageReview)[30]$5,999 (128 GB, 1 TB, GX10-GG0010BN, ASUS eShop US, Oct 30, 2026)[32]
Dell Pro Precision with GB10 (model FCM1253; launched as Dell Pro Max with GB10)Dell128 GB LPDDR5x up to 8533 MT/s onboard (64 GB option also listed)[33]273 GB/s (128 GB LPDDR5x, 256-bit)[34]—gpt-oss-120b, vLLM online serving, equal ISL/OSL: 68.57 tok/s at batch 1 rising to 670.83 tok/s aggregate at batch 64 (StorageReview)[35]$7,901.00 (default FCM1253, 128 GB, 2 TB Gen4 QLC); 4 TB TLC SED SSD option +$2,450.00; 64 GB option listed at a $2,150.00 difference (Dell.com US, read Nov 10, 2026)[36]
Framework Desktop (Ryzen AI Max+ PRO 495, 192 GB)Framework192 GB LPDDR5X-8533 soldered[37]273 GB/s (256-bit)[37]——$6,799 (Max+ PRO 495 192 GB DIY Edition pre-order, Nov 3, 2026; storage not included)[38]
GIGABYTE AI TOP ATOMGIGABYTE128 GB unified system memory[39]273 GB/s (LPDDR5x-8533, 256-bit)[40]—gpt-oss-120b, vLLM online serving, equal ISL/OSL: 60.71 tok/s at batch 1 rising to 649.62 tok/s aggregate at batch 64 (StorageReview)[40]$7,499.99 (128 GB, 4 TB PCIe 4.0) and $9,405.63 (128 GB, 4 TB PCIe 5.0; more options from $7,999.99); 128 GB from $5,999.99 (1 TB) and $6,999.99 (2 TB) at Newegg US, read Nov 9, 2026[41]
GMKtec EVO-X5 Pro AI Mini PCGMKtec192 GB LPDDR5X-8533 onboard (8 x 24 GB, non-upgradeable); up to 160 GB allocatable as VRAM[42]Up to 273 GB/s[43]—GMKtec Laboratory table: GLM-5.3-Flash UD-IQ4_XS (146.05 GB) decode 17.79 tok/s, prefill 70.18, TTFT 14.71 s; Qwen3.8-Flash-Next ROCmFP4-FAST (93.48 GB) decode 45.08 tok/s[42]$6,799 (192 GB/2 TB) and $7,099 (192 GB/4 TB), all variants available, GMKtec US store, read Nov 9, 2026[42]
HP ZGX Nano AI Station (G1n)HP128 GB coherent unified system memory[44]273 GB/s (128 GB LPDDR5x)[45]GB10: up to 1 PFLOP FP4, theoretical, using the sparsity feature; HP and reviewers list 1,000 TOPS FP4 (sparse)[31]gpt-oss-120b, vLLM online serving, equal ISL/OSL: 69.6 tok/s at batch 1 rising to 722.9 tok/s aggregate at batch 64 (StorageReview)[46]$7,399.00 at the HP Store for the 4 TB model; $4,759 on Amazon (Notebookcheck, review updated Oct 5, 2026)[47]
Lenovo ThinkStation PGXLenovo128 GB LPDDR5X unified (256-bit)[48]273 GB/s[48]——US from $5,079 (1 TB base model) on Lenovo's site, per TechRadar's review (Jun 9, 2026); UK from GBP 5,200[49]
MSI EdgeMesa N AI+ (128 GB, X-005US)MSI128 GB LPDDR5X unified system memory[50]273 GB/s[50]——$7,999.00 (128 GB, 4 TB, X-005US, MSI US store, read Nov 11, 2026)[50]
MSI EdgeXpert (MS-C931)MSI64 GB or 128 GB LPDDR5x unified (256-bit)[51]273 GB/s[51]1 PFLOPS FP4 (sparse)[51]—No list price; MSI sells via quote (Get a quote)[51]
NVIDIA DGX SparkNVIDIA (partner GB10 systems from Acer, ASUS, Dell, GIGABYTE, HP, Lenovo and MSI)128 GB; a 64 GB configuration is sold only through OEM partners[31]273 GB/s[31]Up to 1 PFLOP FP4 (theoretical, using the sparsity feature) (sparse)[31]Qwen 3.8 27B (dense) with multi-token prediction: decode of about 20 tokens/s, with time-to-first-token staying interactive out to the full 262K context.[52]$6,950.00 (128 GB, 4 TB) on NVIDIA's enterprise marketplace with an Add To Cart button in a copy cached 07:59 UTC on 2026-10-31; stock unverified (listed out of stock on 2026-10-21); 64 GB partner systems from $4,999[53]
NVIDIA DGX Spark 64 GBNVIDIA (sold by Acer, ASUS, Dell, Gigabyte, HP and MSI)64 GB LPDDR5X unified (two units pool 128 GB over ConnectX-7)[54]273 GB/s (256-bit; NVIDIA spec table covers both 64 GB and 128 GB)[31]1 PFLOPS FP4 (sparse; NVIDIA spec table covers both memory configurations)[31]—from $4,999 (partner systems, Oct 2026; no Founders Edition)[54]
Sipeed MaixStationSipeed128 GB LPDDR5X (256-bit)[28]273 GB/s (Sipeed claim)[28]256 TOPS FP4 (native FP4, no sparsity; Axera/Sipeed claim)[28]—about $3,999 expected for 128 GB, with Kickstarter launch discounts (Sipeed to Tom's Hardware, Oct 2026)[28]
AMD Ryzen AI Halo Developer PlatformAMD128 GB LPDDR5x-8000 unified[55]256 GB/s[55]—gpt-oss-120b, vLLM online serving, equal ISL/OSL 256/256: 222 tok/s aggregate at batch 64 vs 701 on DGX Spark (StorageReview)[56]$3,999 with 2 TB SSD (Jul 2026)[56]
Framework Desktop (Ryzen AI Max+ 395)Framework128 GB LPDDR5x-8000 soldered (32 GB and 64 GB options)[57]256 GB/s[58]—gpt-oss-120b MXFP4 in LM Studio (out-of-the-box setup): roughly 45 tok/s (ServeTheHome; Ryzen AI Max+ 395, 128 GB, Windows 11 Pro)[59]$3,449 (DIY Edition, Max+ 395 with 128 GB, system only; out of stock, Nov 3, 2026)[60]
Acer Veriton GN100 AI Mini WorkstationAcer128 GB LPDDR5x coherent unified[61]——gpt-oss-120b, vLLM, total token throughput: prefill heavy 303.61 to 2,777.56 tok/s; decode heavy 38.38 to 292.41 tok/s (batch 1 to 64, StorageReview)[62]from $3,999 in North America (announced Sep 3, 2025; prices vary by region)[61]
ASRock Industrial AI BOX-A395ASRock Industrial128 GB LPDDR5X-8000 soldered[63]——AgentSTH V7, 32 threads: 15% ahead of the next-closest Ryzen AI Max+ 395 box (single-core within 1%); estimated SPEC CPU2026 int rate: top of a 44% spread across four 395 systems; measured by ServeTheHome, Ubuntu 26.04[64]—
Beelink GTR9 Pro (Ryzen AI Max+ 495, 128 GB)Beelink128 GB LPDDR5X-8533 unified (soldered)[65]—132 AI TOPS on Beelink's page; AMD lists the PRO 495 at Overall TOPS up to 132 and NPU TOPS up to 55; no precision stated by either[65]4.24 tok/s, LM Studio, Qwen3.8-35B-A3B (Beelink's own figure on its store page; quantization, context, backend and RAM size not stated)[65]$4,799 (128 GB/2 TB), Beelink store, pre-order (read Nov 13, 2026)[65]
Beelink GTR9 Pro (Ryzen AI Max+ 495, 192 GB)Beelink192 GB LPDDR5X-8533 unified (soldered)[65]—132 AI TOPS on Beelink's page; AMD lists the PRO 495 at Overall TOPS up to 132 and NPU TOPS up to 55; no precision stated by either[65]4.24 tok/s, LM Studio, Qwen3.8-35B-A3B (Beelink's own figure on its store page; quantization, context, backend and RAM size not stated)[65]$7,399 (192 GB/2 TB) or $7,799 (192 GB/4 TB), Beelink store, pre-order (read Nov 13, 2026)[65]
Bosgame M5 MAX AI Mini PCBosgame192 GB unified LPDDR5 (soldered); up to 160 GB allocatable to the GPU[66]———$6,199 introductory first-batch pre-order price (192 GB, 2 TB PCIe 4.0 SSD), from Nov 3, 2026, until the first allocation sells out[66]
Dell Pro Max Micro (FCM2250)Dell24 GB GDDR7 on the RTX PRO 4000 SFF (23.9 GB usable measured) + 96 GB DDR5-6400 CSODIMM system RAM in StorageReview's tested build[67]——Ministral 3 8B, llama.cpp server (CUDA), 4,096-in/1,024-out: 52.0 tok/s at 1 request, 108.9 at 4; TTFT 1,477 ms (StorageReview, RTX PRO 4000 SFF 24 GB, driver 595.99.02, Ubuntu 26.04.1)[67]From $1,449.00 on Dell.com US; RTX PRO 4000 SFF 24 GB option +$3,870.00 (read Nov 16, 2026)[68]
Dell Pro Precision 9 T4DellUp to 2x 96 GB GDDR7 (two RTX PRO 6000 Max-Q) + up to 4 TB DDR5 RDIMM in 16 slots, 8 channels[69]——MiniMax M2.7 Q4_K_M (129.3 GB) split across 2x RTX PRO 6000 Max-Q: 83.7 tok/s one user, 127.3 peak; 30.3 on one card plus system RAM (StorageReview, llama.cpp b11716, Ubuntu 26.04.1)[69]From $5,925.00 on Dell.com US; dual RTX PRO 6000 Max-Q option +$30,820.00 (read Nov 14, 2026). StorageReview's tested build (Xeon 698X, 256 GB, 2x Max-Q) about $66,600[70]
Dell Pro Precision with GB300 (model FCT6263; announced as Dell Pro Max with GB300)Dell252 GB HBM3e GPU + 496 GB LPDDR5X CPU[71]———$160,195.00 (Dell.com US default config FCT6263, read Nov 8, 2026)[71]
Gigabyte AI TOP Aeroup to 128 GB LPDDR5X unified[72]————
GMKtec EVO-X2 AI Mini PCGMKtec64 GB or 128 GB onboard LPDDR5X-8000 (non-upgradeable)[73]——Llama 3.3 70B Q6_K Instruct: 3.7-3.8 tok/s generation fully on the Radeon 8060S (about 2 tok/s CPU-only); Qwen3-32B 10.4-10.5 tok/s; 128 GB unit, short prompt, tool not named (ServeTheHome)[74]$3,499.99 (128 GB/1 TB) and $3,649.99 (128 GB/2 TB), each against a $3,999.99 compare-at price (GMKtec US store, read Nov 11, 2026)[73]
HP Z2 Mini G1a WorkstationHPup to 128 GB unified, up to 96 GB assignable to the GPU, up to 8000 MT/s[75]—up to 50 NPU TOPS[75]gpt-oss-120b GGUF (63.39 GB, full GPU offload) in LM Studio: close to 40 tok/s (StorageReview)[76]$4,781 list for StorageReview's review configuration; about $3,300 street (B&H top spec with 2 TB SSD at $3,342.65, Aug 2025)[76]
Microsoft Surface RTX Spark Dev BoxMicrosoft128 GB unified memory[77]—up to 1 PFLOP of AI compute (Microsoft; precision and sparsity not stated on the page) (sparse)[77]—From $5,999.99 (Microsoft Store US, pre-order, read Nov 1, 2026)[77]
MSI EdgeMesa N AI+ (64 GB)————from $4,699 in the US (64 GB soldered LPDDR5X, 1 TB PCIe Gen 5)[78]
Tenstorrent TT-QuietBox 2 (Blackhole)Tenstorrent128 GB GDDR6 on the accelerators + 256 GB DDR5-5600 system memory[79]———$9,999 (Oct 30, 2026)[79]
WiCi One (RTX 5060 Ti edition)WiCi16 GB GDDR7 VRAM; 1 TB NVMe 4 SSD for TurboStream weight paging (WiCi's claim: NVMe used as working VRAM). System RAM not stated[80]———$2,599 list (WiCi shop, Oct 2026); a $600-off code (WICIWELCOME) is applied at checkout. Early-access price was $1,999 (Notebookcheck, Engadget, Sep 2026)[80]
WiCi One (RTX 5090 edition)WiCi32 GB GDDR7 VRAM; 4 TB NVMe 5 SSD for TurboStream weight paging (WiCi's claim: NVMe used as working VRAM). System RAM not stated[80]———$9,999 list (WiCi shop, Oct 2026); a $600-off code (WICIWELCOME) is applied at checkout[80]

Italic values are reported by an outlet or measured by an independent lab; the rest come from the maker. Measured speeds use different models, quantizations and tools, so read each with its source rather than against the others. Voltgrid News does not test hardware itself.

Sources (80)
  1. [1] ASUS
  2. [2] ASUS
  3. [3] StorageReview
  4. [4] Central Computers
  5. [5] HP
  6. [6] StorageReview
  7. [7] HP
  8. [8] StorageReview
  9. [9] Newegg
  10. [10] NVIDIA
  11. [11] Exxact
  12. [12] Supermicro
  13. [13] ServeTheHome
  14. [14] ServeTheHome
  15. [15] TechRadar
  16. [16] NVIDIA
  17. [17] StorageReview
  18. [18] NVIDIA
  19. [19] Apple
  20. [20] Tom's Hardware
  21. [21] MacRumors
  22. [22] Corsair
  23. [23] StorageReview
  24. [24] NVIDIA
  25. [25] ServeTheHome
  26. [26] StorageReview
  27. [27] NVIDIA
  28. [28] Tom's Hardware
  29. [29] ASUS
  30. [30] StorageReview
  31. [31] NVIDIA
  32. [32] ASUS eShop
  33. [33] Dell
  34. [34] HotHardware
  35. [35] StorageReview
  36. [36] Dell
  37. [37] Framework Blog
  38. [38] Framework
  39. [39] GIGABYTE (PR Newswire)
  40. [40] StorageReview
  41. [41] Newegg
  42. [42] GMKtec
  43. [43] GMKtec
  44. [44] HP
  45. [45] HotHardware
  46. [46] StorageReview
  47. [47] Notebookcheck
  48. [48] Lenovo PSREF
  49. [49] TechRadar
  50. [50] MSI
  51. [51] MSI
  52. [52] Tom's Hardware
  53. [53] NVIDIA Marketplace
  54. [54] NVIDIA Blog
  55. [55] AMD
  56. [56] StorageReview
  57. [57] Framework
  58. [58] Framework Blog
  59. [59] ServeTheHome
  60. [60] Framework
  61. [61] Acer
  62. [62] StorageReview
  63. [63] ServeTheHome
  64. [64] ServeTheHome
  65. [65] Beelink
  66. [66] Notebookcheck
  67. [67] StorageReview
  68. [68] Dell
  69. [69] StorageReview
  70. [70] Dell
  71. [71] Dell
  72. [72] Notebookcheck
  73. [73] GMKtec
  74. [74] ServeTheHome
  75. [75] HP
  76. [76] StorageReview
  77. [77] Microsoft
  78. [78] Notebookcheck
  79. [79] Tenstorrent
  80. [80] WiCi

Sources

Published
Sources
4 cited