XiaomiMiMo · First MLX build 21 Sept 2026
MiMo-V2.6-Flash-RL
MLX
Text mit
A 309B parameter text generation model from XiaomiMiMo, with one MLX build at MXFP4.
- Parameters
- 309B From Hugging Face
- Quantisation
- MXFP4 MiMo-V2.6-Flash-RL-mxfp4-q8
- Memory needed
- 197 GB Estimate, unified memory
- Download
- 174 GB Weights, estimated
- Downloads
- 794 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 197 GB at MXFP4
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8 --prompt "Hello"MLX builds
1 on mlx-community| MiMo-V2.6-Flash-RL-mxfp4-q8 | MXFP4 | 174 GB | 197 GB | 794 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.