How much VRAM does MiniMax M2.7 need?
MiniMax M2.7 needs 129 GB for its weights at 4-bit, 132 GB with an 8K context and 138 GB with 32K.
- Parameters
- 229B
- Active per token
- 10B
- Longest context
- 200K
- Released
- Apr 2026
- License
- MiniMax Non-Commercial
- Strongest at
- Coding, Agents
Memory at each precision
| Precision | Weights | With 8K | With 32K | With 128K |
|---|---|---|---|---|
| As released (FP8) | 214 GB | 217 GB | 223 GB | 246 GB |
| 6-bit | 175 GB | 178 GB | 183 GB | 207 GB |
| 5-bit | 151 GB | 154 GB | 160 GB | 183 GB |
| 4-bit | 129 GB | 132 GB | 138 GB | 161 GB |
| 3-bit | 104 GB | 107 GB | 113 GB | 136 GB |
| 2-bit | 79.9 GB | 82.7 GB | 88.5 GB | 112 GB |
| 1.6-bit | 43.9 GB | 46.8 GB | 52.6 GB | 75.9 GB |
One conversation, 16-bit context cache, runtime overhead included.
What runs it
| Machine | Best fit | Context | Speed | First reply |
|---|---|---|---|---|
| RTX 3060 12 GB | Too big | |||
| RTX 4060 Ti 16 GB | Too big | |||
| RTX 3090 | Too big | |||
| RTX 4090 | Too big | |||
| RTX 5090 | Too big | |||
| 2× RTX 3090 | Too big | |||
| RTX PRO 6000 Blackwell | 2-bit | 40K | 149 tok/s | 0.5 s |
| M4 Max 128 GB | 2-bit | 40K | 52 tok/s | 10 s |
| M5 Max 128 GB | 2-bit | 40K | 55 tok/s | 3.0 s |
| Ryzen AI Max+ 395 128 GB | 2-bit | 40K | 33 tok/s | 6.0 s |
| DGX Spark 128 GB | 3-bit | 36K | 34 tok/s | 2.3 s |
| M3 Ultra 256 GB | 6-bit | 28K | 42 tok/s | 5.9 s |
| M5 Ultra 512 GB | FP8 | 200K | 46 tok/s | 1.8 s |
| H100 SXM | Too big | |||
| DGX Station GB300 | FP8 | 96K | 174 tok/s | 0.2 s |
| 8× H200 NVL | FP8 | 200K | 149 tok/s | 0.1 s |
Best fit is the highest quality, up to 8-bit, that leaves 16K of context. First reply is the wait for a 2K prompt. Speeds are rough, plus or minus 25%.
How to run it
- llama.cpp
llama-server -hf unsloth/MiniMax-M2.7-GGUF- vLLM
vllm serve MiniMaxAI/MiniMax-M2.7- MLX (Mac)
mlx_lm.chat --model mlx-community/MiniMax-M2.7-4bit
Questions
How much VRAM does MiniMax M2.7 need?
MiniMax M2.7 needs 129 GB for its weights at 4-bit, 132 GB with an 8K context and 138 GB with 32K.
Can MiniMax M2.7 run on an RTX 4090?
Not on one card. The smallest machine here that runs it is the RTX PRO 6000 Blackwell.