# Run a frontier-class MoE on 128 GB to 512 GB of unified memory (slim)

> Run a frontier-class MoE on 128 GB to 512 GB of unified memory: 3 companies fully do it, 14 with a limit, 90 carry the tag. Every listing in Open-weight models with the reason and a source.

- Full: https://www.anchorterminal.com/niches/open-weights.big-model-on-big-box/index.md (~4,850 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/niches/open-weights.big-model-on-big-box/index.json · canonical https://www.anchorterminal.com/niches/open-weights.big-model-on-big-box/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-15
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Two or three companies' docs show a full fit. Full fit: 3 companies, with a limit: 14, tagged: 90. Weight 10, 6 accounts.

Done when: The model loads and holds a 64K context in memory without swapping.
yes: deepseek-v3-2 (DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.))
yes: gpt-oss-120b (OpenAI (named as publisher on the card; the openai-api listing's terms name OpenAI OpCo, LLC))
yes: laguna-s-2-1 (Poolside, Inc. (named in Poolside's Terms of Use))
caveat: deepseek-v4-1-flash (DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.))
caveat: deepseek-v4-flash-0731 (DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.))
caveat: glm-4-5-air (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))
caveat: glm-5-3 (JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai). The licence names Z.AI)
caveat: glm-5-3-flash (Z.AI Co., Ltd (named in the licence's copyright line))
caveat: hy3 (Tencent (named in the LICENSE file's copyright line))
caveat: inkling (Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary))
caveat: inkling-small (Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary))
caveat: kolibri-1 (Aleph Alpha GmbH)
caveat: minimax-m2-5 (MiniMax AI (named in the licences; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore))
caveat: minimax-m2-7 (MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore))
caveat: minimax-m3-1-flash (MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore))
caveat: mistral-large-4 (Mistral AI (RCS Paris 952 418 325))
caveat: nemotron-3-super-120b-a12b (NVIDIA Corporation)
caveat: nemotron-3-ultra-550b-a55b (NVIDIA Corporation)
caveat: ornith-1-5-397b (Ornith)
caveat: qwen3-5-122b-a10b (Alibaba Cloud (named in the licence's copyright line))
caveat: qwen3-5-397b-a17b (Alibaba Cloud (named in the licence's copyright line))
caveat: qwen3-8-flash-next (Alibaba Cloud (Singapore) Private Limited, the registrant of qwen.ai. The licence names Qwen as copyright holder)
caveat: swift-1-5-qwen3-8-flash-next (UkisAI)

Data: https://www.anchorterminal.com/api/v1/use-cases/open-weights.big-model-on-big-box.json
