VoltgridNews

Mechrevo Master Road X10 RTX Spark PC Starts at CNY 32,999 in China

Mechrevo's Master Road X10 went on sale in China on Nov. 19, IT Home reported. Mechrevo claims 300 GB/s and 140 W; there is no independent test and no US price yet.

Local AI Desk

6 min read

Mechrevo Master Road X10 1.25-litre RTX Spark mini PC with a hexagonal metal front grille on a dark pedestal, official Mechrevo product image

The Mechrevo Master Road X10, an RTX Spark mini PC that went on sale in China on Nov. 19 (Mechrevo product image).

Image: Mechrevo

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

The Mechrevo Master Road X10, a 1.25-litre mini PC built on NVIDIA's RTX Spark N1X, went on sale in China on Nov. 19 at CNY 32,999 with 64 GB of unified memory and CNY 49,999 with 128 GB, IT Home reported that day.

Notebookcheck followed on Nov. 20 with the same configurations and prices, which it credits to IT Home, and says sale outside China is unconfirmed. Its dollar figures, about $4,950 and $7,500, are its own conversions, not list prices. Notebookcheck first wrote about the machine in October; the Nov. 19 sale is the first time Mechrevo has attached prices and a full spec list to it.

The X10 matters to local-model buyers for one reason: in China it now undercuts the two RTX Spark mini PCs that independent labs have already measured on list price, though at 128 GB it carries 2 TB of storage against 4 TB on both, and the ASUS 64 GB model includes 2 TB against the X10's 1 TB. Every performance figure for the X10 itself, though, is still Mechrevo's own claim. Nobody has published a tokens-per-second number for it.

Master Road X10 Specs and Mechrevo's Claimed Figures

Inside is the RTX Spark N1X, which pairs a 20-core Grace CPU with a Blackwell GPU carrying 6,144 CUDA cores, according to Notebookcheck. The CPU and GPU share one pool of unified memory, which NVIDIA lists as LPDDR5X for RTX Spark (the reports on Mechrevo's machine do not name the memory type), 64 GB with a 1 TB SSD or 128 GB with a 2 TB SSD. That shared pool is the spec that decides which models fit: the GPU can be handed a large share of it, so a quantized model far larger than a gaming card's memory can still load.

Mechrevo claims 300 GB/s of memory bandwidth, 1 PFLOPS of sparse FP4 compute and a 140 W TDP, according to IT Home. The 300 GB/s claim equals ASUS's 300 GB/s for the ProArt GR1X and ServeTheHome's reported figure of up to 300 GB/s from LPDDR5X-9400 on a 256-bit bus. MSI's US store lists 273 GB/s for the EdgeMesa N on the same chip, and NVIDIA's RTX Spark page lists no bandwidth, so the gap between makers is unresolved.

The chassis measures 155 x 158 x 51 mm and weighs 1.42 kg, IT Home reported, in all-metal CNC with two turbine fans and a 70-fin heatsink. Ports are four USB-C, one HDMI 2.1 and one 10GbE RJ-45, with Wi-Fi 7, Bluetooth 5.4 and a Kensington lock slot. Mechrevo pitches it as an enterprise desktop AI host and promises day-0 support for AI software, a claim with no detail behind it in the reports.

Why Memory Bandwidth Sets Local Model Speed

A language model writes one token at a time, and each token means reading the model's active weights from memory. On RTX Spark the CPU and GPU share one pool of unified memory, so that pool's speed, 300 GB/s by Mechrevo's claim, is the main limit on how fast a single request decodes. The 1 PFLOPS figure is a peak for FP4 maths that Mechrevo labels sparse, and a chip with more peak compute but slower memory can still generate more slowly.

For a team sharing one box, throughput with several requests at once is the better guide than single-request speed. StorageReview's eight-request runs on the sibling boxes, set out below, are the nearest reference; the X10 has not been measured on either load.

Master Road X10 Price Against MSI and ASUS in China

Price. IT Home's own launch reports give the comparison in one currency. MSI's EdgeMesa N AI+ went on sale in China on Nov. 18 at CNY 33,999 for 64 GB with 1 TB and CNY 56,999 for 128 GB with 4 TB. ASUS's ProArt GR1X started the same day at CNY 34,999 for 64 GB with 2 TB and CNY 54,999 for 128 GB with 4 TB. The X10 undercuts MSI by CNY 1,000 at 64 GB with the same storage. At 128 GB it is CNY 5,000 below ASUS and CNY 7,000 below MSI, but it ships with 2 TB rather than 4 TB, so part of that gap is storage.

In China the X10 lists below MSI and ASUS at both memory sizes, but at 128 GB it carries 2 TB of storage against 4 TB on the other two.

Graphic: Voltgrid News

AI SSD. Mechrevo's proprietary AI SSD offloads model data from system memory to NAND flash so that larger models can run, Notebookcheck reports. Mechrevo has shown it on other machines: on a 32 GB laptop, it says a 35B model's time to first response fell from over 14 seconds to just over 2 seconds. That is a vendor demonstration on different hardware. Notebookcheck notes there is no independent test, and the demo measured the wait before the first answer, not how fast tokens come once weights sit on flash rather than in 300 GB/s memory.

Power and size. The 140 W figure is not an edge over the strongest rivals. NVIDIA's spec tables give RTX Spark compact desktops 140 W, MSI rates the EdgeMesa N at 140 W sustained and ASUS built the GR1X's cooler to hold 140 W. The exception is Microsoft's Surface RTX Spark Dev Box, which lists a 100 W thermal envelope. Nor is it clearly smaller: StorageReview works the EdgeMesa N out to 1.18 litres from its dimensions (MSI advertises 1.3 litres) and the GR1X to 1.15, against Mechrevo's 1.25 for the X10. Gigabyte's AI TOP Aero is about 1 litre, per Notebookcheck.

Which Local Models Fit the 64 GB and 128 GB Versions

The X10 is meant for a team that wants a model on a desk rather than in the cloud, on a compact box with a 10GbE port. What fits depends on the memory tier. NVIDIA says RTX Spark systems run models of up to 120B parameters, and ASUS ties the 70B and 120B classes to its 128 GB configuration.

The independent results on sibling boxes show where the line falls in practice. On the 128 GB EdgeMesa N, StorageReview ran a 35B coding-agent model and Qwen-Image 20B at Q8, with 62.5 GB of memory presented to the GPU by default; its suite ran neither on the 64 GB GR1X. On StorageReview's results for the sibling boxes, the 64 GB GR1X handled models up to the 27B class, so a buyer who needs more than that should look at the CNY 49,999 tier; the X10 itself is untested and its default memory split is not stated.

What StorageReview Measured on Sibling RTX Spark Boxes

StorageReview's runs are the closest reference, and both machines use the same N1X chip and 140 W class as the X10. On Qwen3.8 27B at Q4_K_M, served with llama.cpp on Windows 11, the 128 GB EdgeMesa N wrote 13.0 tokens per second for one request and 39.8 with eight concurrent requests. The 64 GB GR1X wrote 13.1 and 40.0. Our reviews of the MSI EdgeMesa N and the ASUS ProArt GR1X set out those runs.

None of those figures belongs to the X10. Makers set their own firmware, fan curves, memory allocation and storage, and StorageReview found the GR1X's bundled 1 TB Gen4 SSD slow to load a model. Until someone measures the X10 on the same model and tool, the only honest statement is that it uses the same chip.

In the US, Notebookcheck lists the EdgeMesa N from $4,399 and the GR1X from $4,499, both with 64 GB and 1 TB; MSI's US store lists the 128 GB EdgeMesa N at $7,499.00, read on Nov. 21. Microsoft lists the 128 GB Surface Dev Box from $5,999.99 on pre-order. The X10 has no US price.

What Is Still Unknown About the Master Road X10

No outlet has published a token rate, a sustained-power trace, a noise figure or a thermal reading for the X10. The reports read do not say which operating system it ships with, how its memory is split between CPU and GPU by default, or whether AI SSD comes in the box and on which configurations. IT Home reported on Oct. 11, citing a tipster, that the X10 would carry AI SSD; the Nov. 19 sale reports do not confirm it. How AI SSD behaves with a model larger than memory, and what it costs in generation speed, is untested on any machine.

The next markers are a first independent LLM measurement of the X10 and any listing outside China with a dollar price. Neither has a date. The figures that would settle it are a run on Qwen3.8 27B at Q4_K_M in llama.cpp, so it can sit beside StorageReview's EdgeMesa N and GR1X numbers, and a 35B-or-larger model on the 128 GB unit with and without AI SSD.

How it compares

Full table
Mechrevo Master Road X10 RTX Spark PC Starts at CNY 32,999 in China: 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 34 machines
Mechrevo Master Road X10 RTX Spark PC Starts at CNY 32,999 in China: how the machine compares with other local AI hardware: the other machines
ProductMemoryBandwidthAI computeMeasured speedPrice
ASUS ProArt GR1XASUS64 GB or up to 128 GB LPDDR5X unified memory (ASUS spec page, read Nov 18, 2026)[24]300 GB/s (ASUS spec page, read Nov 18, 2026)[24]WITHDRAWN, not a sparse figure: ASUS and NVIDIA say 'up to 1 petaFLOP FP4' with no sparse or dense label; no field asserts either[25]Qwen3.8 27B Q4_K_M, llama.cpp CUDA, Windows 11: 13.1 tok/s output at 1 request, 31.4 at 4, 40.0 at 8 requests; TTFT 8.6 s (StorageReview, 64 GB unit, sr-client 1.13)[26]$4,499 (64 GB, 1 TB Gen4, Windows 11 Home) at ASUS eShop US; $4,499.99 at Best Buy, which lists 64 GB/2 TB at $4,999.99 (StorageReview, Nov 18, 2026)[26]
Mechrevo Master Road X10Mechrevo64 GB (with 1 TB SSD) or 128 GB (with 2 TB SSD) unified memory[27]300 GB/s (unified memory)[27]up to 1 PFLOP FP4 (sparse)[27]—CNY 32,999 (64 GB/1 TB) to CNY 49,999 (128 GB/2 TB), China only[27]
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)[25]Up to 300 GB/s: LPDDR5X-9400 on a 256-bit bus (NVIDIA's product page lists no bandwidth)[28]—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)[29]Laptops from $2,599; pricing and configurations vary by region[30]
AMD Ryzen AI Halo (Ryzen AI Max+ PRO 495, 192 GB)AMD192 GB LPDDR5X (256-bit)[31]273 GB/s[31]——$7,299.99 for the Linux version (released the week of Oct 12, 2026); Windows version coming soon[31]
ASUS Ascent GX10ASUS64 GB or 128 GB LPDDR5X-8533 unified[32]273 GB/s (8533 MT/s), as listed by StorageReview; ASUS's spec page states no bandwidth[33]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)[34]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)[33]$5,999 (128 GB, 1 TB, GX10-GG0010BN, ASUS eShop US, Oct 30, 2026)[35]
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)[36]273 GB/s (128 GB LPDDR5x, 256-bit)[37]—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)[38]$7,901.00 (default FCM1253, 128 GB, 2 TB Gen4 QLC) on Dell.com US, unchanged; 64 GB memory option listed at -$2,150.00, 4 TB TLC SED SSD +$2,450.00 (read Nov 20, 2026)[39]
Framework Desktop (Ryzen AI Max+ PRO 495, 192 GB)Framework192 GB LPDDR5X-8533 soldered[40]273 GB/s (256-bit)[40]——$6,799 (Max+ PRO 495 192 GB DIY Edition pre-order, Nov 3, 2026; storage not included)[41]
GIGABYTE AI TOP ATOMGIGABYTE128 GB unified system memory[42]273 GB/s (LPDDR5x-8533, 256-bit)[43]—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)[43]$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[44]
GMKtec EVO-X5 Pro AI Mini PCGMKtec192 GB LPDDR5X-8533 onboard (8 x 24 GB, non-upgradeable); up to 160 GB allocatable as VRAM[45]Up to 273 GB/s[46]—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[45]$6,799 (192 GB/2 TB) and $7,099 (192 GB/4 TB), all variants available, GMKtec US store, read Nov 9, 2026[45]
HP ZGX Nano AI Station (G1n)HP128 GB coherent unified system memory[47]273 GB/s (128 GB LPDDR5x)[48]GB10: up to 1 PFLOP FP4, theoretical, using the sparsity feature; HP and reviewers list 1,000 TOPS FP4 (sparse)[34]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)[49]$7,399.00 at the HP Store for the 4 TB model; $4,759 on Amazon (Notebookcheck, review updated Oct 5, 2026)[50]
Lenovo ThinkStation PGXLenovo128 GB LPDDR5X unified (256-bit)[51]273 GB/s[51]Up to 1 PFLOP FP4 (Lenovo PSREF gives no sparsity label; XDA says NVIDIA's figure assumes structured sparsity) (sparse)[51]Qwen3-Coder-Next FP8 (FP8 KV cache), vLLM NGC container, one request at a time, 170K context: 25-40 tok/s (XDA Developers, Lenovo-loaned unit)[52]US from $5,079 (1 TB base model) on Lenovo's site, per TechRadar's review (Jun 9, 2026); UK from GBP 5,200[53]
MSI EdgeMesa N AI+ (128 GB, X-005US)MSI128 GB LPDDR5X unified system memory[54]273 GB/s[54]—Qwen3.8 27B Q4_K_M, llama.cpp CUDA, Windows 11: 13.0 tok/s output at 1 request, 31.1 at 4, 39.8 at 8 requests (StorageReview, 128 GB unit, default 62.5 GB GPU allocation)[55]$7,499.00 (128 GB, 4 TB, X-005US, MSI US store, out of stock, read Nov 21, 2026)[54]
MSI EdgeXpert (MS-C931)MSI64 GB or 128 GB LPDDR5x unified (256-bit)[56]273 GB/s[56]1 PFLOPS FP4 (sparse)[56]—No list price; MSI sells via quote (Get a quote)[56]
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[34]273 GB/s[34]Up to 1 PFLOP FP4 (theoretical, using the sparsity feature) (sparse)[34]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.[57]$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[58]
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)[59]273 GB/s (256-bit; NVIDIA spec table covers both 64 GB and 128 GB)[34]1 PFLOPS FP4 (sparse; NVIDIA spec table covers both memory configurations)[34]—from $4,999 (partner systems, Oct 2026; no Founders Edition)[59]
Sipeed MaixStationSipeed128 GB LPDDR5X (256-bit)[31]273 GB/s (Sipeed claim)[31]256 TOPS FP4 (native FP4, no sparsity; Axera/Sipeed claim)[31]—about $3,999 expected for 128 GB, with Kickstarter launch discounts (Sipeed to Tom's Hardware, Oct 2026)[31]
AMD Ryzen AI Halo Developer PlatformAMD128 GB LPDDR5x-8000 unified[60]256 GB/s[60]—gpt-oss-120b, vLLM online serving, equal ISL/OSL 256/256: 222 tok/s aggregate at batch 64 vs 701 on DGX Spark (StorageReview)[61]$3,999 with 2 TB SSD (Jul 2026)[61]
Framework Desktop (Ryzen AI Max+ 395)Framework128 GB LPDDR5x-8000 soldered (32 GB and 64 GB options)[62]256 GB/s[63]—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)[64]$3,449 (DIY Edition, Max+ 395 with 128 GB, system only; out of stock, Nov 3, 2026)[65]
Acer Veriton GN100 AI Mini WorkstationAcer128 GB LPDDR5x coherent unified[66]——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)[67]from $3,999 in North America (announced Sep 3, 2025; prices vary by region)[66]
ASRock Industrial AI BOX-A395ASRock Industrial128 GB LPDDR5X-8000 soldered[68]——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[69]—
Beelink GTR9 Pro (Ryzen AI Max+ 495, 128 GB)Beelink128 GB LPDDR5X-8533 unified (soldered)[70]—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[70]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)[70]$4,799 (128 GB/2 TB), Beelink store, pre-order (read Nov 13, 2026)[70]
Beelink GTR9 Pro (Ryzen AI Max+ 495, 192 GB)Beelink192 GB LPDDR5X-8533 unified (soldered)[70]—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[70]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)[70]$7,399 (192 GB/2 TB) or $7,799 (192 GB/4 TB), Beelink store, pre-order (read Nov 13, 2026)[70]
Bosgame M5 MAX AI Mini PCBosgame192 GB unified LPDDR5 (soldered); up to 160 GB allocatable to the GPU[71]———$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[71]
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[72]——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)[72]From $1,449.00 on Dell.com US; RTX PRO 4000 SFF 24 GB option +$3,870.00 (read Nov 16, 2026)[73]
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[74]——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)[74]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[75]
Dell Pro Precision with GB300 (model FCT6263; announced as Dell Pro Max with GB300)Dell252 GB HBM3e GPU + 496 GB LPDDR5X CPU[76]———$160,195.00 (Dell.com US default config FCT6263, read Nov 8, 2026)[76]
Gigabyte AI TOP Aeroup to 128 GB LPDDR5X unified[77]————
GMKtec EVO-X2 AI Mini PCGMKtec64 GB or 128 GB onboard LPDDR5X-8000 (non-upgradeable)[78]——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)[79]$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)[78]
HP Z2 Mini G1a WorkstationHPup to 128 GB unified, up to 96 GB assignable to the GPU, up to 8000 MT/s[80]—up to 50 NPU TOPS[80]gpt-oss-120b GGUF (63.39 GB, full GPU offload) in LM Studio: close to 40 tok/s (StorageReview)[81]$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)[81]
Microsoft Surface RTX Spark Dev BoxMicrosoft128 GB unified memory[82]—up to 1 PFLOP of AI compute (Microsoft; precision and sparsity not stated on the page) (sparse)[82]—From $5,999.99 (Microsoft Store US, pre-order, read Nov 1, 2026)[82]
MSI EdgeMesa N AI+ (64 GB)————$4,399 (64 GB / 1 TB, after MSI's cut from $4,699; Nov 2026)[83]
Tenstorrent TT-QuietBox 2 (Blackhole)Tenstorrent128 GB GDDR6 on the accelerators + 256 GB DDR5-5600 system memory[84]———$9,999 (Oct 30, 2026)[84]
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[85]———$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)[85]
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[85]———$9,999 list (WiCi shop, Oct 2026); a $600-off code (WICIWELCOME) is applied at checkout[85]

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 (85)
  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] ASUS
  25. [25] NVIDIA
  26. [26] StorageReview
  27. [27] Notebookcheck
  28. [28] ServeTheHome
  29. [29] StorageReview
  30. [30] NVIDIA
  31. [31] Tom's Hardware
  32. [32] ASUS
  33. [33] StorageReview
  34. [34] NVIDIA
  35. [35] ASUS eShop
  36. [36] Dell
  37. [37] HotHardware
  38. [38] StorageReview
  39. [39] Dell
  40. [40] Framework Blog
  41. [41] Framework
  42. [42] GIGABYTE (PR Newswire)
  43. [43] StorageReview
  44. [44] Newegg
  45. [45] GMKtec
  46. [46] GMKtec
  47. [47] HP
  48. [48] HotHardware
  49. [49] StorageReview
  50. [50] Notebookcheck
  51. [51] Lenovo PSREF
  52. [52] XDA Developers
  53. [53] TechRadar
  54. [54] MSI
  55. [55] StorageReview
  56. [56] MSI
  57. [57] Tom's Hardware
  58. [58] NVIDIA Marketplace
  59. [59] NVIDIA Blog
  60. [60] AMD
  61. [61] StorageReview
  62. [62] Framework
  63. [63] Framework Blog
  64. [64] ServeTheHome
  65. [65] Framework
  66. [66] Acer
  67. [67] StorageReview
  68. [68] ServeTheHome
  69. [69] ServeTheHome
  70. [70] Beelink
  71. [71] Notebookcheck
  72. [72] StorageReview
  73. [73] Dell
  74. [74] StorageReview
  75. [75] Dell
  76. [76] Dell
  77. [77] Notebookcheck
  78. [78] GMKtec
  79. [79] ServeTheHome
  80. [80] HP
  81. [81] StorageReview
  82. [82] Microsoft
  83. [83] Notebookcheck
  84. [84] Tenstorrent
  85. [85] WiCi

Sources

Published
Sources
6 cited