- Size
- 229B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, MiniMax Model LicenseOur reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 22 Oct 2025the date the repo was created
- Context length
- 192k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)MiniMaxM2ForCausalLM
- On Hugging Face
- MiniMaxAI/MiniMax-M2112k downloads in the last 30 days, 1.5k likes
Scores
- default setting25.0%simple-bench.com
Epoch's name: MiniMax-M2. Best closed model on this set: claude-fable-5-2_unknown, 94.9% (Anthropic). All 125 results
- Agent: Terminus 230.0%±2.727 Oct 2025, tbench.ai
Epoch's name: MiniMax-M2. Best closed model on this set: gpt-5.5_unknown, 84.7% (OpenAI). All 202 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 1.9 GB, worked out from the model's config (MiniMaxAI/MiniMax-M2), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
unsloth/MiniMax-M2-GGUF (converted by unsloth), 6.2k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| UD-IQ3_XXS | 87.2 GBfile size, 2 parts | 89.6 GB87.2 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:UD-IQ3_XXSDownload hf download unsloth/MiniMax-M2-GGUF --include "UD-IQ3_XXS/MiniMax-M2-UD-IQ3_XXS-*-of-00002.gguf" --local-dir MiniMax-M2-GGUF |
| Q3_K_S | 91.9 GBfile size, 2 parts | 94.4 GB91.9 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q3_K_SDownload hf download unsloth/MiniMax-M2-GGUF --include "Q3_K_S/MiniMax-M2-Q3_K_S-*-of-00002.gguf" --local-dir MiniMax-M2-GGUF |
| UD-Q3_K_XL | 94.5 GBfile size, 3 parts | 96.9 GB94.5 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:UD-Q3_K_XLDownload hf download unsloth/MiniMax-M2-GGUF --include "UD-Q3_K_XL/MiniMax-M2-UD-Q3_K_XL-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| Q3_K_M | 101.8 GBfile size, 3 parts | 104.2 GB101.8 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q3_K_MDownload hf download unsloth/MiniMax-M2-GGUF --include "Q3_K_M/MiniMax-M2-Q3_K_M-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| IQ4_XS | 113.5 GBfile size, 3 parts | 116.0 GB113.5 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:IQ4_XSDownload hf download unsloth/MiniMax-M2-GGUF --include "IQ4_XS/MiniMax-M2-IQ4_XS-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| IQ4_NL | 120.1 GBfile size, 3 parts | 122.6 GB120.1 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:IQ4_NLDownload hf download unsloth/MiniMax-M2-GGUF --include "IQ4_NL/MiniMax-M2-IQ4_NL-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| Q4_0 | 120.6 GBfile size, 3 parts | 123.0 GB120.6 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q4_0Download hf download unsloth/MiniMax-M2-GGUF --include "Q4_0/MiniMax-M2-Q4_0-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| Q4_K_S | 121.1 GBfile size, 3 parts | 123.5 GB121.1 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q4_K_SDownload hf download unsloth/MiniMax-M2-GGUF --include "Q4_K_S/MiniMax-M2-Q4_K_S-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| UD-Q4_K_XL | 122.6 GBfile size, 3 parts | 125.0 GB122.6 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:UD-Q4_K_XLDownload hf download unsloth/MiniMax-M2-GGUF --include "UD-Q4_K_XL/MiniMax-M2-UD-Q4_K_XL-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| Q4_K_M | 128.8 GBfile size, 3 parts | 131.3 GB128.8 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q4_K_MDownload hf download unsloth/MiniMax-M2-GGUF --include "Q4_K_M/MiniMax-M2-Q4_K_M-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| Q4_1 | 133.4 GBfile size, 3 parts | 135.8 GB133.4 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q4_1Download hf download unsloth/MiniMax-M2-GGUF --include "Q4_1/MiniMax-M2-Q4_1-*-of-00003.gguf" --local-dir MiniMax-M2-GGUF |
| Q5_K_S | 146.7 GBfile size, 4 parts | 149.1 GB146.7 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q5_K_SDownload hf download unsloth/MiniMax-M2-GGUF --include "Q5_K_S/MiniMax-M2-Q5_K_S-*-of-00004.gguf" --local-dir MiniMax-M2-GGUF |
| UD-Q5_K_XL | 151.0 GBfile size, 4 parts | 153.4 GB151.0 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:UD-Q5_K_XLDownload hf download unsloth/MiniMax-M2-GGUF --include "UD-Q5_K_XL/MiniMax-M2-UD-Q5_K_XL-*-of-00004.gguf" --local-dir MiniMax-M2-GGUF |
| Q5_K_M | 151.2 GBfile size, 4 parts | 153.6 GB151.2 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q5_K_MDownload hf download unsloth/MiniMax-M2-GGUF --include "Q5_K_M/MiniMax-M2-Q5_K_M-*-of-00004.gguf" --local-dir MiniMax-M2-GGUF |
| Q6_K | 174.9 GBfile size, 4 parts | 177.3 GB174.9 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q6_KDownload hf download unsloth/MiniMax-M2-GGUF --include "Q6_K/MiniMax-M2-Q6_K-*-of-00004.gguf" --local-dir MiniMax-M2-GGUF |
| UD-Q6_K_XL | 180.9 GBfile size, 4 parts | 183.4 GB180.9 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:UD-Q6_K_XLDownload hf download unsloth/MiniMax-M2-GGUF --include "UD-Q6_K_XL/MiniMax-M2-UD-Q6_K_XL-*-of-00004.gguf" --local-dir MiniMax-M2-GGUF |
| Q8_0 | 226.4 GBfile size, 5 parts | 228.9 GB226.4 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:Q8_0Download hf download unsloth/MiniMax-M2-GGUF --include "Q8_0/MiniMax-M2-Q8_0-*-of-00005.gguf" --local-dir MiniMax-M2-GGUF |
| UD-Q8_K_XL | 243.4 GBfile size, 6 parts | 245.9 GB243.4 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:UD-Q8_K_XLDownload hf download unsloth/MiniMax-M2-GGUF --include "UD-Q8_K_XL/MiniMax-M2-UD-Q8_K_XL-*-of-00006.gguf" --local-dir MiniMax-M2-GGUF |
| BF16 | 426.1 GBfile size, 10 parts | 428.5 GB426.1 + 1.9 + 0.50 | Commandsllama.cpp llama-server -hf unsloth/MiniMax-M2-GGUF:BF16Download hf download unsloth/MiniMax-M2-GGUF --include "BF16/MiniMax-M2-BF16-*-of-00010.gguf" --local-dir MiniMax-M2-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 6bitlmstudio-community/MiniMax-M2-MLX-6bit | 173.1 GBfile size | 175.5 GB173.1 + 1.9 + 0.50 | Download page |
| MLX 8bitlmstudio-community/MiniMax-M2-MLX-8bit | 226.3 GBfile size | 228.7 GB226.3 + 1.9 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F8_E4M3original weights | 214.3 GBfile size | 216.7 GB214.3 + 1.9 + 0.50 |
hf download MiniMaxAI/MiniMax-M2 --local-dir MiniMax-M2Other conversions (14; sizes not read)
- QuantTrio/MiniMax-M2-AWQ AWQ, 177 downloads
- cerebras/MiniMax-M2-REAP-162B-A10B FP8, 129 downloads
- cerebras/MiniMax-M2-REAP-139B-A10B FP8, 124 downloads
- cerebras/MiniMax-M2-REAP-172B-A10B FP8, 115 downloads
- gauravmm/MiniMax-M2.5-REAP-139B-A10B-NVFP4 NVFP4, 75 downloads
- lukealonso/MiniMax-M2-NVFP4 NVFP4, 69 downloads
- cyankiwi/MiniMax-M2-AWQ-4bit AWQ, 4bit, 69 downloads
- ArtusDev/MiniMaxAI_MiniMax-M2-EXL3 EXL3, 31 downloads
- ModelCloud/MiniMax-M2-GPTQMODEL-W4A16 GPTQ, w4a16, 24 downloads
- turboderp/MiniMax-M2-exl3 EXL3, 23 downloads
- avtc/MiniMax-M2-GPTQMODEL-W4A16 GPTQ, w4a16, 22 downloads
- a2s-ai/MiniMax-M2-AWQ AWQ, 20 downloads
- ludovicoYIN/MiniMax-M2-BF16-W4A16 AWQ, bf16, 15 downloads
- morriszjm/MiniMax-M2.5-192e FP8, 15 downloads
The Hub tags 39 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.