How much VRAM does MiMo V2.6 Pro need?
MiMo V2.6 Pro needs 527 GB for its weights as released (FP4 + FP8), 529 GB with an 8K context and 530 GB with 32K.
- Parameters
- 1T
- Active per token
- 42B
- Longest context
- 1M
- Released
- Sep 2026
- License
- MIT
- Strongest at
- Chat, Coding, Agents, Docs
Memory at each precision
| Precision | Weights | With 8K | With 32K | With 128K |
|---|---|---|---|---|
| As released (FP4 + FP8) | 527 GB | 529 GB | 530 GB | 534 GB |
| 3-bit | 466 GB | 468 GB | 469 GB | 473 GB |
| 2-bit | 358 GB | 359 GB | 360 GB | 365 GB |
| 1.6-bit | 197 GB | 198 GB | 199 GB | 204 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 | Too big | |||
| M4 Max 128 GB | Too big | |||
| M5 Max 128 GB | Too big | |||
| Ryzen AI Max+ 395 128 GB | Too big | |||
| DGX Spark 128 GB | Too big | |||
| M3 Ultra 256 GB | Too big | |||
| M5 Ultra 512 GB | 2-bit | 128K | 33 tok/s | 8.1 s |
| H100 SXM | Too big | |||
| DGX Station GB300 | 1.6-bit | 832K | 168 tok/s | 0.7 s |
| 8× H200 NVL | FP4 + FP8 | 1M | 71 tok/s | 0.4 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 ggml-org/MiMo-V2.6-Pro-RL-GGUF- vLLM
vllm serve XiaomiMiMo/MiMo-V2.6-Pro-RL- MLX (Mac)
mlx_lm.chat --model mlx-community/MiMo-V2.6-Pro-RL-mxfp4-q8
Questions
How much VRAM does MiMo V2.6 Pro need?
MiMo V2.6 Pro needs 527 GB for its weights as released (FP4 + FP8), 529 GB with an 8K context and 530 GB with 32K.
Can MiMo V2.6 Pro run on an RTX 4090?
Not on one card. The smallest machine here that runs it is the M5 Ultra 512 GB.