4-bit Open on Hugging Face
Parameters
426B
Weights (est.)
≈ 243 GB
Mac memory (est.)
512 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/MiniMax-M3.1-Flash-Text-4bit --prompt "Hello"
Details
- Base model
- MiniMaxAI/MiniMax-M3.1-Flash (quantized)
- Vendor
- MiniMaxAI
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- minimax-community
- Downloads
- 1.3K in the last 30 days · 1.3K all time · 5 likes
- Published
- 2026-10-23 · updated 2026-10-23 (19d ago)
- Tags
- minimax_m3_vl, agent, coding, custom_code
Other MLX builds of MiniMaxAI/MiniMax-M3.1-Flash
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MiniMax-M3.1-Flash-Text-3bit | 3-bit | ≈ 186 GB | 256 GB+ | 2.9K |
| MiniMax-M3.1-Flash-oQ3e-mtp | 3-bit | ≈ 188 GB | 256 GB+ | 1.0K |
| MiniMax-M3.1-Flash-oQ3.5e-mtp | 3-bit | ≈ 188 GB | 256 GB+ | 689 |
| MiniMax-M3.1-Flash-oQ4e-mtp | 4-bit | ≈ 241 GB | 512 GB+ | 1.2K |
| MiniMax-M3.1-Flash-Text-4bit (this one) | 4-bit | ≈ 243 GB | 512 GB+ | 1.3K |