MSI EdgeMesa N RTX Spark Mini PC Lists at $7,999; Gigabyte Aero Unpriced
MSI's EdgeMesa N, an RTX Spark mini PC, lists at $7,999 with 128 GB at 273 GB/s and was out of stock on Nov. 11; the 64 GB model is reported at $4,699. Gigabyte's AI TOP Aero has no price.
Local AI DeskEdited by Ege Erten
7 min readAI-assisted

MSI's US store lists the 128 GB EdgeMesa N at $7,999; the 64 GB model is reported at $4,699. Gigabyte's AI TOP Aero has no price.
Illustration (AI-generated)
MSI's US store listed the 128 GB EdgeMesa N AI+, one of the first RTX Spark mini PCs, built on NVIDIA's chip, at $7,999.00 on Nov. 11, 2026, and showed it out of stock.

MSI's 128 GB EdgeMesa N lists at $7,999, the highest listed price in the set; the 64 GB price is reported by Notebookcheck.
Illustration (AI-generated)
Two RTX Spark mini desktops surfaced within a day. Gigabyte launched its AI TOP Aero on Nov. 10, Notebookcheck reported, without a price. Notebookcheck then reported on Nov. 11 that MSI's EdgeMesa N was on sale in the US, ahead of Gigabyte's machine, from $4,699 with 64 GB of memory. NVIDIA had said on Oct. 7 that compact RTX Spark desktops would go on sale in November, so these are the first of that wave. No lab has published a language-model measurement of either desktop yet, so this file sets out what the makers state, what reviewers measured on other RTX Spark and GB10 machines, and what remains open.
What the RTX Spark Mini PC Is
RTX Spark is NVIDIA's Windows PC superchip. It pairs a 20-core Arm CPU with a Blackwell RTX GPU through one pool of unified memory. It was announced on May 31, 2026, at GTC Taipei, and has shipped in laptops since October. Our RTX Spark laptop review and the earlier laptop product file cover that side.
MSI's store page lists the EdgeMesa N X-005US with a 20-core Arm CPU (10 Cortex-X925 and 10 Cortex-A725 cores at up to 3.25 GHz, per MSI; NVIDIA's own page gives the core count but not the core types or clocks), a 6,144-core Blackwell RTX GPU, 128 GB of LPDDR5x unified memory at 273 GB/s, a 4 TB Gen5 NVMe drive and Windows 11 Pro. The box measures 5.98 by 5.79 by 2.17 inches, weighs about 5.5 lb and runs from a 240 W power adapter. MSI gives a three-year limited warranty. MSI's datasheet lists four 20 Gbps USB-C ports, one HDMI 2.1b output, one 10 Gb Ethernet port and Wi-Fi 7. The store's spec table says HDMI 2.1a, so MSI's own pages disagree on that point.
According to Notebookcheck, the 64 GB model costs $4,699 with a 1 TB PCIe Gen 5 drive. The case is 1.3 litres of aluminium, cooled by a vapour chamber and two fans rated for up to 140 W. The memory is soldered, and there is a single M.2 2242 slot for storage. The $4,699 figure is Notebookcheck's. MSI's page for that model could not be read, so Voltgrid has not seen the price on MSI's store.
Gigabyte's AI TOP Aero uses the same top RTX Spark chip, with 20 CPU cores and 6,144 CUDA cores, in a case of roughly 1 litre, according to Notebookcheck. It has up to 128 GB of LPDDR5X, up to 4 TB of PCIe 5.0 storage, USB-C, 10 GbE and Wi-Fi 7. Gigabyte's own newsroom and product pages could not be read, so every Aero specification here is as Notebookcheck reported it. Gigabyte has given no memory bandwidth and no price.
What's New in the EdgeMesa N and AI TOP Aero
The chip is not new; the shape is. Until now, a buyer who wanted this much unified memory on a desk had two routes. One was a DGX Spark or a partner GB10 box running NVIDIA's Linux-based DGX OS. The other was an RTX Spark laptop running Windows. These desktops put the RTX Spark chip in a box the size of a DGX Spark, with Windows 11 Pro. RTX Spark and GB10 are separate NVIDIA products.
Memory bandwidth sets how fast a model writes once it fits. MSI lists 273 GB/s for the EdgeMesa N, the same figure NVIDIA gives for both the 64 GB and 128 GB DGX Spark. ServeTheHome, writing about RTX Spark laptops, reported a higher ceiling of up to 300 GB/s from LPDDR5X-9400 on a 256-bit bus. NVIDIA's own RTX Spark page gives no bandwidth figure, so MSI's 273 GB/s is the only maker-stated number for a desktop, and MSI does not say why it is lower.
What MSI's datasheet does not list matters too. DGX Spark carries a ConnectX-7 network card at 200 Gbps, which lets two to four units pool memory for larger models. The EdgeMesa N's listed ports stop at 10 Gb Ethernet, so a 200 Gbps link between two boxes is not on offer. Gigabyte instead points to NVIDIA's Personal AI Router (PAIR), which Notebookcheck says spreads inference jobs across devices on a local network. Gigabyte also names LM Studio, Ollama, NVIDIA's Nemotron models and CUDA as supported.
MSI and NVIDIA both say the platform delivers up to 1 petaflop of FP4 AI performance, a vendor claim. Neither MSI's page nor NVIDIA's RTX Spark page says whether that figure is sparse or dense; NVIDIA labels the similar DGX Spark figure as theoretical, using sparsity.
What a Local AI Mini PC Should Solve
The target buyer wants a model in the 70B to 120B class held in memory on a Windows desk, without a cloud bill and without a laptop's thermal limits. NVIDIA rates RTX Spark for models of up to 120 billion parameters with a 1-million-token context, a vendor claim. A desktop also sidesteps the laptop throttling question. StorageReview measured the N1X CPU at up to 98 C in sustained loads on the Dell XPS 16 and HP OmniBook Ultra 16 laptops.
The closest measured reference is a different machine. StorageReview ran Qwen3.6-35B-A3B, a mixture-of-experts model, in a Codex CLI coding-agent task at a 64K context on HP's 128 GB OmniBook Ultra 16 laptop. It generated 89.5 tokens per second on Windows and passed three of three runs; the quantization was not stated in the figures cited here. On a GB10 desktop, Tom's Hardware measured the DGX Spark at about 20 tokens per second decoding the dense Qwen 3.8 27B with multi-token prediction, with quantization and software not stated in the figures cited here. The two results use different models, tools and operating systems, so they do not compare with each other. Neither was taken on an EdgeMesa N or an AI TOP Aero, and neither should be read as one.
Price is where the desktops have to argue their case. At 128 GB and 273 GB/s, MSI lists $7,999, against the $6,950 DGX Spark listing on NVIDIA's enterprise marketplace, a price read on Oct. 31 with stock unverified. At 64 GB, Notebookcheck reports $4,699 for MSI, against the $4,999 at which 64 GB DGX Spark partner systems started on Oct. 23. Notebookcheck put Gigabyte's GB10-based AI TOP Atom at $4,999 with 64 GB and a 2 TB drive. Below all of them sit AMD Strix Halo boxes at lower bandwidth. The Framework Desktop with 128 GB listed at $3,449 at 256 GB/s, though it was out of stock on Nov. 4, and GMKtec's EVO-X2 with 128 GB was $3,499.99 on Nov. 10.
Why Memory Size and Speed Decide Local AI
A language model has to sit in memory before it can run, so capacity decides which models fit. MSI's EdgeMesa N AI+ carries 128 GB of unified memory that the CPU and GPU share, and NVIDIA rates the RTX Spark platform for models of up to 120 billion parameters, a vendor claim.
Speed is a separate limit. To write each new word, the chip reads the model's weights from memory, so memory bandwidth, the rate at which data moves, usually caps how fast text appears. MSI lists 273 GB/s for the EdgeMesa N. That is a ceiling, not a measurement: no one has published tokens per second for these desktops, and a fixed GPU share of memory can shrink what actually fits. A machine can hold a large model and still write slowly.
What Is Not Confirmed Yet
No independent outlet or lab has published a tokens-per-second figure for any RTX Spark desktop. Until one does, decode speed on these boxes is unknown. The shared 273 GB/s figure is not a substitute.
The memory split is the biggest open question for model size. On RTX Spark laptops, StorageReview found that Windows fixes the GPU's share of memory in advance rather than sharing it on demand. Its 64 GB Dell XPS 16, split 32/32, left 30.5 GB usable by the GPU. Whether the desktops ship with a larger GPU share on 128 GB, or let users change it, neither maker has said.
Several other points are open. Gigabyte's AI TOP Aero has no price, no stated bandwidth and no US retail listing. Its specifications rest on one outlet's report of a release Voltgrid could not read. MSI's $4,699 64 GB price rests on Notebookcheck. MSI has given no restock date for the 128 GB model, and non-US prices are unknown. Notebookcheck notes that early RTX Spark reviews found some games failing to launch or crashing. Nothing yet shows whether either desktop holds 140 W under a long inference run, or how loud it gets. MSI lists fan noise of 28 at idle and 32 at full load, without a unit.
Neither maker has announced a review date or an embargo. Gigabyte has not said when the AI TOP Aero will get a US price, and MSI has not said when the 128 GB EdgeMesa N returns to stock. Reviews of the RTX Spark laptops appeared around their Oct. 16 on-sale date, but no outlet has said it has either desktop in hand. When the first measured local-model runs land, with the model, quantization and tool stated, this product file becomes the base for a full review of the machine they cover.
How it compares
Full table| Product | Memory | Bandwidth | AI compute | Measured speed | Price |
|---|---|---|---|---|---|
| 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 StationHP | 252 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] |
| 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)[8] | GPU HBM3e 7.1 TB/s; CPU LPDDR5X 396 GB/s; NVLink-C2C 900 GB/s between them[8] | 15 PFLOPS FP4 (without sparsity)[8] | 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[9] |
| 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[10] | 7.1 TB/s (GPU HBM3E); 396 GB/s (CPU LPDDR5X)[11] | up to 20 PFLOPS FP4 (Supermicro gives no sparsity label; ServeTheHome describes it as sparse FP4)[10] | 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)[12] | $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)[13] |
| NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA (sold through PNY, TD SYNNEX and workstation makers) | 96 GB[14] | 1,792 GB/s[14] | 4,000 AI TOPS (FP4, with sparsity) (sparse)[14] | 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)[15] | $16,000 on NVIDIA's US marketplace (Workstation Edition), listed out of stock[16] |
| Apple Mac Studio (M5 Ultra)Apple | up to 512 GB unified (96 GB on 30-core M5 Ultra; 256 GB or 512 GB on 36-core/80-core M5 Ultra)[17] | 1.2 TB/s[17] | — | 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)[18] | $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)[19] |
| 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)[20] | Up to 300 GB/s: LPDDR5X-9400 on a 256-bit bus (NVIDIA's product page lists no bandwidth)[21] | — | 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)[22] | Laptops from $2,599; pricing and configurations vary by region[23] |
| AMD Ryzen AI Halo (Ryzen AI Max+ PRO 495, 192 GB)AMD | 192 GB LPDDR5X (256-bit)[24] | 273 GB/s[24] | — | — | $7,299.99 for the Linux version (released the week of Oct 12, 2026); Windows version coming soon[24] |
| ASUS Ascent GX10ASUS | 64 GB or 128 GB LPDDR5X-8533 unified[25] | 273 GB/s (8533 MT/s), as listed by StorageReview; ASUS's spec page states no bandwidth[26] | 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)[27] | 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)[26] | $5,999 (128 GB, 1 TB, GX10-GG0010BN, ASUS eShop US, Oct 30, 2026)[28] |
| Dell Pro Precision with GB10 (model FCM1253; launched as Dell Pro Max with GB10)Dell | 128 GB LPDDR5x up to 8533 MT/s onboard (64 GB option also listed)[29] | 273 GB/s (128 GB LPDDR5x, 256-bit)[30] | — | 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)[31] | $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)[32] |
| Framework Desktop (Ryzen AI Max+ PRO 495, 192 GB)Framework | 192 GB LPDDR5X-8533 soldered[33] | 273 GB/s (256-bit)[33] | — | — | $6,799 (Max+ PRO 495 192 GB DIY Edition pre-order, Nov 3, 2026; storage not included)[34] |
| GIGABYTE AI TOP ATOMGIGABYTE | 128 GB unified system memory[35] | 273 GB/s (LPDDR5x-8533, 256-bit)[36] | — | 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)[36] | $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[37] |
| GMKtec EVO-X5 Pro AI Mini PCGMKtec | 192 GB LPDDR5X-8533 onboard (8 x 24 GB, non-upgradeable); up to 160 GB allocatable as VRAM[38] | Up to 273 GB/s[39] | — | 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[38] | $6,799 (192 GB/2 TB) and $7,099 (192 GB/4 TB), all variants available, GMKtec US store, read Nov 9, 2026[38] |
| HP ZGX Nano AI Station (G1n)HP | 128 GB coherent unified system memory[40] | 273 GB/s (128 GB LPDDR5x)[41] | GB10: up to 1 PFLOP FP4, theoretical, using the sparsity feature; HP and reviewers list 1,000 TOPS FP4 (sparse)[27] | 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)[42] | $7,399.00 at the HP Store for the 4 TB model; $4,759 on Amazon (Notebookcheck, review updated Oct 5, 2026)[43] |
| Lenovo ThinkStation PGXLenovo | 128 GB LPDDR5X unified (256-bit)[44] | 273 GB/s[44] | — | — | US from $5,079 (1 TB base model) on Lenovo's site, per TechRadar's review (Jun 9, 2026); UK from GBP 5,200[45] |
| MSI EdgeMesa N AI+ (128 GB, X-005US)MSI | 128 GB LPDDR5X unified system memory[46] | 273 GB/s[46] | — | — | $7,999.00 (128 GB, 4 TB, X-005US, MSI US store, read Nov 11, 2026)[46] |
| MSI EdgeXpert (MS-C931)MSI | 64 GB or 128 GB LPDDR5x unified (256-bit)[47] | 273 GB/s[47] | 1 PFLOPS FP4 (sparse)[47] | — | No list price; MSI sells via quote (Get a quote)[47] |
| 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[27] | 273 GB/s[27] | Up to 1 PFLOP FP4 (theoretical, using the sparsity feature) (sparse)[27] | 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.[48] | $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[49] |
| 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)[50] | 273 GB/s (256-bit; NVIDIA spec table covers both 64 GB and 128 GB)[27] | 1 PFLOPS FP4 (sparse; NVIDIA spec table covers both memory configurations)[27] | — | from $4,999 (partner systems, Oct 2026; no Founders Edition)[50] |
| Sipeed MaixStationSipeed | 128 GB LPDDR5X (256-bit)[24] | 273 GB/s (Sipeed claim)[24] | 256 TOPS FP4 (native FP4, no sparsity; Axera/Sipeed claim)[24] | — | about $3,999 expected for 128 GB, with Kickstarter launch discounts (Sipeed to Tom's Hardware, Oct 2026)[24] |
| AMD Ryzen AI Halo Developer PlatformAMD | 128 GB LPDDR5x-8000 unified[51] | 256 GB/s[51] | — | gpt-oss-120b, vLLM online serving, equal ISL/OSL 256/256: 222 tok/s aggregate at batch 64 vs 701 on DGX Spark (StorageReview)[52] | $3,999 with 2 TB SSD (Jul 2026)[52] |
| Framework Desktop (Ryzen AI Max+ 395)Framework | 128 GB LPDDR5x-8000 soldered (32 GB and 64 GB options)[53] | 256 GB/s[54] | — | 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)[55] | $3,449 (DIY Edition, Max+ 395 with 128 GB, system only; out of stock, Nov 3, 2026)[56] |
| Acer Veriton GN100 AI Mini WorkstationAcer | 128 GB LPDDR5x coherent unified[57] | — | — | 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)[58] | from $3,999 in North America (announced Sep 3, 2025; prices vary by region)[57] |
| ASRock Industrial AI BOX-A395ASRock Industrial | 128 GB LPDDR5X-8000 soldered[59] | — | — | 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[60] | — |
| Bosgame M5 MAX AI Mini PCBosgame | 192 GB unified LPDDR5 (soldered); up to 160 GB allocatable to the GPU[61] | — | — | — | $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[61] |
| Dell Pro Precision with GB300 (model FCT6263; announced as Dell Pro Max with GB300)Dell | 252 GB HBM3e GPU + 496 GB LPDDR5X CPU[62] | — | — | — | $160,195.00 (Dell.com US default config FCT6263, read Nov 8, 2026)[62] |
| Gigabyte AI TOP Aero | up to 128 GB LPDDR5X unified[63] | — | — | — | — |
| GMKtec EVO-X2 AI Mini PCGMKtec | 64 GB or 128 GB onboard LPDDR5X-8000 (non-upgradeable)[64] | — | — | 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)[65] | $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)[64] |
| HP Z2 Mini G1a WorkstationHP | up to 128 GB unified, up to 96 GB assignable to the GPU, up to 8000 MT/s[66] | — | up to 50 NPU TOPS[66] | gpt-oss-120b GGUF (63.39 GB, full GPU offload) in LM Studio: close to 40 tok/s (StorageReview)[67] | $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)[67] |
| Microsoft Surface RTX Spark Dev BoxMicrosoft | 128 GB unified memory[68] | — | up to 1 PFLOP of AI compute (Microsoft; precision and sparsity not stated on the page) (sparse)[68] | — | From $5,999.99 (Microsoft Store US, pre-order, read Nov 1, 2026)[68] |
| MSI EdgeMesa N AI+ (64 GB) | — | — | — | — | from $4,699 in the US (64 GB soldered LPDDR5X, 1 TB PCIe Gen 5)[69] |
| MSI XpertStation WS300MSI (NVIDIA DGX Station platform) | 252 GB HBM3e GPU + 496 GB LPDDR5X CPU (748 GB coherent)[70] | — | — | 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)[70] | $99,999.00 'Start From' at Newegg US (model WS300T60L, 2x 2 TB NVMe RAID1), sold by Newegg as a request-a-quote listing (read Nov 4, 2026)[71] |
| Tenstorrent TT-QuietBox 2 (Blackhole)Tenstorrent | 128 GB GDDR6 on the accelerators + 256 GB DDR5-5600 system memory[72] | — | — | — | $9,999 (Oct 30, 2026)[72] |
| WiCi One (RTX 5060 Ti edition)WiCi | 16 GB GDDR7 VRAM; 1 TB NVMe 4 SSD for TurboStream weight paging (WiCi's claim: NVMe used as working VRAM). System RAM not stated[73] | — | — | — | $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)[73] |
| WiCi One (RTX 5090 edition)WiCi | 32 GB GDDR7 VRAM; 4 TB NVMe 5 SSD for TurboStream weight paging (WiCi's claim: NVMe used as working VRAM). System RAM not stated[73] | — | — | — | $9,999 list (WiCi shop, Oct 2026); a $600-off code (WICIWELCOME) is applied at checkout[73] |
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 (73)
- [1] ASUS
- [2] ASUS
- [3] StorageReview
- [4] Central Computers
- [5] HP
- [6] StorageReview
- [7] HP
- [8] NVIDIA
- [9] Exxact
- [10] Supermicro
- [11] ServeTheHome
- [12] ServeTheHome
- [13] TechRadar
- [14] NVIDIA
- [15] StorageReview
- [16] NVIDIA
- [17] Apple
- [18] Tom's Hardware
- [19] MacRumors
- [20] NVIDIA
- [21] ServeTheHome
- [22] StorageReview
- [23] NVIDIA
- [24] Tom's Hardware
- [25] ASUS
- [26] StorageReview
- [27] NVIDIA
- [28] ASUS eShop
- [29] Dell
- [30] HotHardware
- [31] StorageReview
- [32] Dell
- [33] Framework Blog
- [34] Framework
- [35] GIGABYTE (PR Newswire)
- [36] StorageReview
- [37] Newegg
- [38] GMKtec
- [39] GMKtec
- [40] HP
- [41] HotHardware
- [42] StorageReview
- [43] Notebookcheck
- [44] Lenovo PSREF
- [45] TechRadar
- [46] MSI
- [47] MSI
- [48] Tom's Hardware
- [49] NVIDIA Marketplace
- [50] NVIDIA Blog
- [51] AMD
- [52] StorageReview
- [53] Framework
- [54] Framework Blog
- [55] ServeTheHome
- [56] Framework
- [57] Acer
- [58] StorageReview
- [59] ServeTheHome
- [60] ServeTheHome
- [61] Notebookcheck
- [62] Dell
- [63] Notebookcheck
- [64] GMKtec
- [65] ServeTheHome
- [66] HP
- [67] StorageReview
- [68] Microsoft
- [69] Notebookcheck
- [70] StorageReview
- [71] Newegg
- [72] Tenstorrent
- [73] WiCi







