LLMs · MiniMax
MiniMax M2 (230B-A10B)
- Parameters
- 229B (10.0B active)
- Architecture
- Mixture of experts
- Max context
- 192K tokens
- License
- modified-mit
- Released
- 2025-10
How to run it
Ollama
Ollama only offered this as a cloud model, and has since retired it. To run it locally, use the GGUF files below with llama.cpp or LM Studio.
Quantized files · GGUF
Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.
huggingface.co/unsloth/MiniMax-M2-GGUF (opens in a new tab)
ollama run hf.co/unsloth/MiniMax-M2-GGUFOriginal weights · Hugging Face
Full-precision files from MiniMax, for fine-tuning, vLLM, Transformers.
Official repo · GitHub
Reference code, inference scripts and docs from MiniMax. The weights themselves download from Hugging Face.
github.com/MiniMax-AI/MiniMax-M2 (opens in a new tab)
git clone https://github.com/MiniMax-AI/MiniMax-M2Memory needed
Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.
| Quantization | Quality | Weights | Total at 8K context | Total at 32K context | Download |
|---|---|---|---|---|---|
Q2_K |
Low | 91.5 GB | 94.2 GB | 100 GB | GGUF · folder (opens in a new tab) |
Q3_K_M |
Low | 112 GB | 115 GB | 121 GB | GGUF · folder (opens in a new tab) |
Q4_K_M |
Good | 140 GB | 142 GB | 148 GB | GGUF · folder (opens in a new tab) |
Q5_K_M |
High | 162 GB | 165 GB | 171 GB | GGUF · folder (opens in a new tab) |
Q6_K |
High | 188 GB | 190 GB | 196 GB | GGUF · folder (opens in a new tab) |
Q8_0 |
Very high | 242 GB | 245 GB | 251 GB | GGUF · folder (opens in a new tab) |
F16 |
Full | 457 GB | 460 GB | 466 GB | GGUF · folder (opens in a new tab) Original weights (opens in a new tab) |
Best hardware for MiniMax M2 (230B-A10B)
| Grade · points | Hardware | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 93 ptsExcellent (S) · 93 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M3 Ultra (256 GB) | Q4_K_M | 158 GB / 192 GB | 43.3 tok/s | Runs well |
| 88 ptsExcellent (S) · 88 of 100 points: Model quality 38.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15 | Apple M3 Ultra (512 GB) | Q4_K_M | 173 GB / 384 GB | 43.3 tok/s | Runs well |
| 87 ptsExcellent (S) · 87 of 100 points: Model quality 33.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M2 Ultra (192 GB) | Q3_K_M | 126 GB / 144 GB | 54.7 tok/s | Tight fit |
| 79 ptsGreat (A) · 79 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 12.4/15, Memory use 15.0/15 | NVIDIA GB10 (128 GB) | Q2_K | 103 GB / 115 GB | 27.5 tok/s | Tight fit |
| 68 ptsGood (B) · 68 of 100 points: Model quality 28.0/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15 | Apple M4 Max (128 GB) | Q2_K | 102 GB / 96.0 GB | 40.3 tok/s | Runs with offload |
| 68 ptsGood (B) · 68 of 100 points: Model quality 28.0/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA RTX PRO 6000 Blackwell | Q2_K | 99.0 GB / 96.0 GB | 98.4 tok/s | Runs with offload |
| 63 ptsGood (B) · 63 of 100 points: Model quality 28.0/45, Memory fit 10.0/25, Speed 10.3/15, Memory use 15.0/15 | AMD Ryzen AI Max+ 395 (128 GB) | Q2_K | 102 GB / 96.0 GB | 18.9 tok/s | Runs with offload |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.