Run a frontier-class MoE on 128 GB to 512 GB of unified memory
Two or three companies' docs show a full fit.
What counts as done
The model loads and holds a 64K context in memory without swapping.
Measured, for our own tests: decode at 10 tokens per second or better, prompt processing above 100 tokens per second, and answers in the prompt's language. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: run DeepSeek V4 Flash on my Mac Studio
, what fits a 192 GB Framework Desktop
, GLM-5.3 at Q2 as a reviewer
, MiniMax at 100K context on Strix Halo
Does the job 3
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| DeepSeek-V3.2 C DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.) | Unsloth GGUFs from 161 GB (TQ1_0) to 217 GB (IQ2_XXS) load on 256 to 512 GB under llama.cpp's deepseek2 architecture; MLA keeps the 64K cache near 5 GB. No account times decode or prompt processing. source |
| gpt-oss-120b BB OpenAI (named as publisher on the card; the openai-api listing's terms name OpenAI OpCo, LLC) | 117B MoE at 63 GB MXFP4 with 5.1B active; acc-21 and acc-40 ran it on 128 GB Strix Halo machines alongside other models, Ollama's gpt-oss:120b is 65 GB, llama.cpp has gpt-oss and 64K of cache is about 5 GB. source |
| Laguna S 2.1 C Poolside, Inc. (named in Poolside's Terms of Use) | 96 GB Q4_K_M plus about 12 GiB KV at 64K holds in 128 GB; an account measured 186 tokens per second prompt processing and 27.8 decode at UD-Q4_K_XL, Ollama ships the tag, and llama.cpp lists the laguna architecture. source |
Does the job, with a limit 20
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| DeepSeek V4.1 Flash C DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.) | acc-22 runs it at Q2 on a 192 GB Framework Desktop near 14 tokens per second; llama.cpp has deepseek41 and Unsloth ships IQ1_S (233 GB) to Q4_K_XL (501 GB). Prompt-processing speed is unreported and acc-40 saw Chinese replies from V4 Flash at IQ3. source |
| DeepSeek-V4-Flash-0731 C DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.) | Loads on 128 GB at IQ2 (acc-08, 30 to 35 tokens per second) and Unsloth recommends IQ3_XXS at 103 GB with 110 GB of RAM; llama.cpp has deepseek4. acc-40 saw Chinese answers to English prompts at IQ3_XXS. source |
| GLM-4.5-Air C JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai, per the first batch's check on 21 October 2026) | A 106B MoE, below the 500B class, but Unsloth's Q4_K_XL (68 GB) plus a 12 GB bf16 cache at 64K fits 128 GB with 12B active; glm4moe is in llama.cpp. No account times it. source |
| GLM-5.3 B JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai). The licence names Z.AI | Unsloth's UD-IQ2_M (239 GB) targets 256 GB boxes and llama.cpp has glm-dsa; 40B active at 2 bits has no first-hand speed report, and acc-22 found the Flash cousin too slow for interactive use at Q2. source |
| GLM-5.3-Flash B Z.AI Co., Ltd (named in the licence's copyright line) | 320B MoE with 18B active; Unsloth puts 1-bit at 100 GB and 3-bit at 128 to 150 GB, llama.cpp has glm5-next, and acc-22 reached a usable reviewer at Q2 on 192 GB but calls it slow for interactive work. source |
| Hy3 B Tencent (named in the LICENSE file's copyright line) | 295B MoE with 21B active; AngelSlim ships IQ1_M (89 GB), Q2_K_XL (100 GB), Q3_K_M (135 GB) and Q4_K_M (182 GB) with a llama-server line at 64K and a q8 cache. No first-hand speed or language report. source |
| Inkling B Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary) | 975B MoE; Unsloth's 1-bit needs about 290 GB and 2-bit 325 GB, so only a 512 GB box qualifies. The inkling architecture is not in llama.cpp master's list, so the GGUF path rests on Unsloth's statement that it runs. source |
| Inkling-Small B Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary) | 276B MoE with 12B active; Unsloth's table gives 89 GB at 2-bit and 132 to 170 GB at 4-bit, inside the 128 to 256 GB band, but llama.cpp master lacks the inkling architecture and no account times it. source |
| Kolibri-1 C Aleph Alpha GmbH | A 78B MoE with 3.5B active, under the 500B class; FP8 (78.9 GB) or the Q4 GGUF (49.8 GB) fits 128 GB with a 6.7 GB cache at 64K (40 of 50 layers sliding window). No first-hand speed report. source |
| MiniMax-M2.5 C MiniMax AI (named in the licences; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore) | Unsloth GGUFs from 74 GB (IQ2_XXS) to 131 GB (UD-Q4_K_XL) fit 128 GB to 256 GB, llama.cpp lists MINIMAXM2 and LM Studio states 121 GB minimum, but no account gives decode or prompt-processing speed and every reply spends tokens on thinking. source |
| MiniMax-M2.7 C MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore) | Unsloth GGUFs from 61 GB to 141 GB (UD-Q4_K_XL) fit 128 GB to 256 GB boxes; a second-hand Strix Halo account reached 100K at UD-IQ3_XXS only with mmap off and swap added, and prompt processing was the painful part. source |
| MiniMax-M3.1-Flash C MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore) | Unsloth GGUFs of 135 GB to 249 GB fit 192 GB to 512 GB boxes with a llama.cpp build carrying MiniMax-M3.1, plus a DSpark draft; nothing fits 128 GB and no account gives speeds. source |
| Mistral Large 4 C Mistral AI (RCS Paris 952 418 325) | ggml-org and Unsloth publish GGUFs with mmproj, but only 1 to 2 bit builds (233 GB to 378 GB) fit a 256 GB or 512 GB box, nothing fits 128 GB to 192 GB, and no account gives speeds. source |
| Nemotron 3 Super 120B A12B B NVIDIA Corporation | A 120B rather than 500B-class model, but it is what fits: Unsloth 4-bit needs 64 GB to 72 GB, SEP measured 17 tok/s on a 128 GB Strix Halo after raising the GPU memory limit; prompt-processing speed not given. source |
| Nemotron 3 Ultra 550B A55B B NVIDIA Corporation | Unsloth GGUFs from 188 GB to 360 GB (UD-Q4_K_XL) and a 347 GB MLX 4-bit build fit 256 GB to 512 GB boxes; nothing fits 128 GB or 192 GB, and no account gives speeds for 55B active parameters. source |
| Ornith-1.5-397B C Ornith | Q4_K_M 244 GB plus 1.9 GiB KV fits a 512 GB box and Ollama lists a 397b tag at 242 GB, but Ornith ships no 2 or 3 bit build, no account gives speeds and the licence exists only as a tag. source |
| Qwen3.5-122B-A10B B Alibaba Cloud (named in the licence's copyright line) | Not 500B class, but the 128 GB owners' pick: Ollama 81 GB Q4 or Unsloth UD-Q4_K_XL 77 GB with 1.5 GB of KV at 64K; acc-49 found it accurate but slow. source |
| Qwen3.5-397B-A17B B Alibaba Cloud (named in the licence's copyright line) | The family's 500B-class MoE: Unsloth UD-IQ2_M 123 GB or UD-Q3_K_XL 179 GB with 1.9 GB of KV at 64K fit 192 to 512 GB, but no account runs it and Ollama has no tag. source |
| Qwen3.8-Flash-Next C Alibaba Cloud (Singapore) Private Limited, the registrant of qwen.ai. The licence names Qwen as copyright holder | 125B MoE for 128 GB boxes: Ollama 105 GB MLX on a Mac, Unsloth UD-IQ4_XS 93.7 GB elsewhere, 1.5 GB of KV at 64K; vLLM's stable list lacks the qwen4_exp architecture. source |
| Swift 1.5 Qwen3.8-Flash-Next C UkisAI | 180B-file MoE for 128 GB boxes only through the 66.6 to 84.7 GB GSQ-RCO quants with 1.5 GB of KV at 64K; the qwen4_exp architecture is missing from vLLM's stable list and no account runs it. source |
Doesn't do this job 63
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Agents-A1-4B C Shanghai Artificial Intelligence Laboratory (the InternAgent team there, per the card's recommended system prompt and the template's default prompt); the GitHub LICENSE leaves the copyright line as the Apache template | A 4.5B dense model, not a 500B-class mixture of experts; the use case does not apply. source |
| Apertus v1.5 8B C ETH Zurich and EPFL (the Swiss National AI Institute, named in the Acceptable Use Policy) | An 8.9B dense model, not a 500B-class mixture of experts. source |
| Apodex-1.1-mini C Apodex (the site's copyright line reads 2026 Apodex) | A 36B mixture of experts that fits 32 GB; not the 500B-class checkpoint this use case is about. source |
| BigBang-v1 C The Endless Frontier (endless-frontier) | A 36B mixture of experts, not a 500B-class checkpoint. source |
| Carbon-X C Hugging Face (the HuggingFaceBio organisation, named Hugging Face Biology Research on the Hub) | 14.8B dense, not a 500B-class checkpoint. source |
| Cosmos-Reason2-2B C NVIDIA Corporation | A 2.4B model. source |
| Darwin-36B-Opus C VIDRAFT Inc. (named on vidraft.net); the card's citation names FINAL-Bench and VIDRAFT_LAB | A 35B mixture of experts that fits 32 GB. source |
| DiffusionGemma 26B A4B IT D Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author) | A 25B mixture of experts. source |
| Gemma 4 12B IT BB Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author) | A 12B dense model. source |
| Gemma 4 26B A4B IT BB Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author) | A 26B mixture of experts that fits 24 GB. source |
| Gemma 4 31B IT BB Google LLC (the registrant of gemma.ai; the card names Google DeepMind as author) | A 31B dense model. source |
| Gemma 4 E2B IT C Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author) | A 2B-effective model. source |
| Gemma 4 E4B IT B Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author) | A 4B-effective model. source |
| GLM-4.7-Flash B JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai) | A 30B mixture of experts that fits 24 GB. source |
| gpt-oss-20b B OpenAI (named in USAGE_POLICY and the model card; the LICENSE file's copyright line is the unfilled Apache template) | A 21B mixture of experts that fits 16 GB. source |
| Granite 4.2 3B C International Business Machines Corporation (per IBM's naming guidance, as read for granite-guardian) | A 3.7B dense model. source |
| InternVL3.5-GPT-OSS-20B-A4B-Preview D Shanghai AI Laboratory (OpenGVLab), not named in the repository | A 21B mixture of experts. source |
| Kimi K3 B Moonshot AI (the licence names Moonshot AI; the Kimi Platform terms name Moonshot AI PTE. LTD.) | Unsloth's table puts the smallest dynamic 1-bit at 610 GB of memory and the 466 GB UD-Q1_0 has no quality figure; a 512 GB machine falls short. llama.cpp has kimi-k3. source |
| Kronos C No company. Yu Shi publishes it from the GitHub account shiyu-coder and the Hugging Face user account NeoQuasar (named ShiYu), with co-authors at Tsinghua University per the paper | Largest size is Kronos-base, 0.43 GB in FP32; not a mixture-of-experts language model. |
| Laguna M.1 C Poolside, Inc. (named in Poolside's Terms of Use; the LICENSE.md copyright line reads Poolside) | No GGUF or MLX build from Poolside or third parties was found, and the 139 GB NVFP4 build needs NVIDIA Blackwell GPUs rather than unified memory. source |
| Laguna XS 2.1 C Poolside, Inc. (named in Poolside's Terms of Use) | 33B model; does not aim at the 500B-class use case. |
| LBS-27B C inclusionAI, Ant Group (named in the site footer of inclusion-ai.org); the work is credited to authors from Wuhan University of Technology, CASIA, Zhejiang University and Ant Group | 27B dense vision model; not the use case. |
| LFM2.5-2.6B D Liquid AI, Inc. (the licensor named in the LFM Open License) | 2.6B model. |
| Ling-3.0-tiny C Ant Intelligence (Hang Zhou) Technology Co., Ltd (named as provider in the training-content summary); inclusionAI, Ant Group in the site footer of inclusion-ai.org | 7.9B model. |
| MiMo-V2.6 Distill Qwen 9B C Xiaomi (the card and report name Xiaomi MiMo; no LICENSE file names a copyright holder) | 9B model. |
| MiniCPM-o 4.5 C OpenBMB (named as the MiniCPM-o team on the technical report; the GitHub LICENSE is the unfilled Apache template) | 9.4B model. |
| MiniCPM5-2B C OpenBMB (named in the GitHub LICENSE's copyright line) | 2.5B model. |
| Muse Glimmer 30B BB Meta (the verified Hugging Face organisation is "Meta Inc.", the card names Meta Superintelligence Lab, and the licence carries no copyright line) | A 30B dense model, not a 500B-class mixture of experts. source |
| Nanbeige4.3-33B C BOSS Zhipin (Kanzhun Limited), unconfirmed | A 33B dense model, not a 500B-class mixture of experts. source |
| NVIDIA Nemotron 3.5 Bolt E4B 4GB C NVIDIA Corporation | An 8B (4B effective) model, not a 500B-class mixture of experts. source |
| Nemotron 3.5 Lightning 30B A3B B NVIDIA Corporation | A 30B mixture of experts, not a 500B-class model. source |
| Nemotron 3 Nano 30B A3B B NVIDIA Corporation | A 30B mixture of experts, not a 500B-class model. source |
| Nemotron 3 Nano 4B C NVIDIA Corporation | A 4B model, not a 500B-class mixture of experts. source |
| Nemotron 3 Nano Omni 30B A3B Reasoning C NVIDIA Corporation | A 31B mixture of experts, not a 500B-class model. source |
| occamy-1.0 C Accio (Accio-Lab) | A 35B mixture of experts, not a 500B-class model. source |
| Olmo 3 7B Think D The Allen Institute for Artificial Intelligence (Ai2), a 501(c)(3) nonprofit, per its Responsible Use Guidelines | A 7B dense model, not a 500B-class mixture of experts. source |
| Ornith-1.5-35B-A3B C Ornith | 35B model. |
| Ornith-1.5-9B C Ornith | 9B model. |
| Qwen3-30B-A3B-Instruct-2507 C Alibaba Cloud (named in the licence's copyright line) | A 30B mixture of experts, not a 500B-class model. source |
| Qwen3-4B-Instruct-2507 C Alibaba Cloud (named in the licence's copyright line) | A 4B dense model, not a 500B-class mixture of experts. source |
| Qwen3.5-0.8B D Alibaba Cloud (named in the licence's copyright line) | A small dense model, not a 500B-class mixture of experts. source |
| Qwen3.5-2B D Alibaba Cloud (named in the licence's copyright line) | A small dense model, not a 500B-class mixture of experts. source |
| Qwen3.5-4B C Alibaba Cloud (named in the licence's copyright line) | A 4B dense model, not a 500B-class mixture of experts. source |
| Qwen3.5-9B C Alibaba Cloud (named in the licence's copyright line) | A 9B dense model, not a 500B-class mixture of experts. source |
| Qwen3.6-27B B Alibaba Cloud (named in the licence's copyright line) | A 27B dense model, not a 500B-class mixture of experts. source |
| Qwen3.6-35B-A3B B Alibaba Cloud (named in the licence's copyright line) | A 35B mixture of experts with 3B active, not 500B class. source |
| Qwen3.8-27B B Alibaba Cloud (named in the licence's copyright line) | A 27B dense model, not a 500B-class mixture of experts. source |
| Qwen3-Coder-30B-A3B-Instruct C Alibaba Cloud (named in the licence's copyright line) | A 30B mixture of experts, not 500B class. source |
| Qwen3-Coder-Next C Alibaba Cloud (the Qwen team's employer; no LICENSE file names a copyright holder for this model) | An 80B mixture of experts that fits 64 GB; not the 500B-class job this use case describes. source |
| Qwen3-Omni-30B-A3B-Instruct D Alibaba Cloud (carried from the 20 October 2026 pilot; this model's files name no copyright holder) | A 30B mixture of experts, not 500B class. source |
| Qwen3-VL-2B-Instruct C Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder) | Not a 500B-class mixture of experts. source |
| Qwen3-VL-30B-A3B-Instruct C Alibaba Cloud (per the pilot's RDAP check of qwen.ai; this model's files name no copyright holder) | Not a 500B-class mixture of experts. source |
| Qwen3-VL-32B-Instruct C Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder) | Not a 500B-class mixture of experts. source |
| Qwen3-VL-4B-Instruct D Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder) | Not a 500B-class mixture of experts. source |
| Qwen3-VL-8B-Instruct C Alibaba Cloud (per the pilot's RDAP check of qwen.ai; this model's files name no copyright holder) | Not a 500B-class mixture of experts. source |
| Qwopus3.8-27B-Flash-V2 C Jackrong, an individual Hugging Face account | A 27B dense fine-tune, not a 500B-class mixture of experts. source |
| Recursive Flint C Recursive Superintelligence, Inc. (the Hugging Face organisation's full name) | A 40B mixture of experts with 2.5B active, not 500B class. source |
| Ripple-65B Preview D Ricursive Intelligence, Inc. | A 65B dense model, not a 500B-class mixture of experts, and no publisher GGUF. source |
| SmolLM3-3B C Hugging Face, Inc. | A 3B dense model, not a 500B-class mixture of experts. source |
| Spark-X2.6-4B C XHToken (the licence's copyright line); the Hugging Face organisation's name is SparkLLM | A 4B dense model, not a 500B-class mixture of experts. source |
| Swift 1.5 Qwen3.8-27B C UkisAI | A 27B dense fine-tune, not a 500B-class mixture of experts. source |
| ThinkingCap (Qwen3.8 27B) C BottleCap AI (named in the licence's copyright line) | A 27B dense fine-tune, not a 500B-class mixture of experts. source |
| Baidu Unlimited-OCR-2 C Baidu, Inc. | A 3.3B OCR model, not a 500B-class mixture of experts. source |
28 listings in the category were added after this reading and aren't marked yet.
What stops agents finishing
- smallest build larger than the machine at any precision
- prompt processing so slow that one agent turn takes minutes
- model answers in Chinese to English prompts at IQ3
- runtime support only in a nightly or Docker tag
Around it
Before: open-weights.local-coding-agent. After: coding-agents.plan-review.
Where this comes from
Weight 10 of 100 in Open-weight models: 6 of 51 accounts, all from owners of 128 GB or larger machines
The same as data: /api/v1/use-cases/open-weights.big-model-on-big-box.json, or the MCP tool get_use_case with id open-weights.big-model-on-big-box. Other jobs in this category: /api/v1/niches?category=open-weights.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.