4-bit Open on Hugging Face
Parameters
139B
Weights (est.)
≈ 78.3 GB
Mac memory (est.)
96 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-M2.1-REAP-40-4bit --prompt "Hello"
Details
- Base model
- 0xSero/MiniMax-M2.1-139B (quantized)
- Vendor
- 0xSero
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 37 in the last 30 days · 927 all time · 0 likes
- Published
- 2026-01-14 · updated 2026-01-14 (10mo ago)
- Tags
- minimax_m2, minimax, reap, pruned, custom_code
Other MLX builds of 0xSero/MiniMax-M2.1-139B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| MiniMax-M2.1-REAP-40-4bit (this one) | 4-bit | ≈ 78.3 GB | 96 GB+ | 37 |
| MiniMax-M2.1-REAP-40-5bit | 5-bit | ≈ 95.7 GB | 128 GB+ | 23 |
| MiniMax-M2.1-REAP-40-8bit | 8-bit | ≈ 148 GB | 192 GB+ | 18 |