MXFP4 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-REAP-139B-A10B-mxfp4 --prompt "Hello"
Details
- Base model
- cerebras/MiniMax-M2-REAP-139B-A10B (quantized)
- Vendor
- cerebras
- Task
- Text generation
- Quantisation
- MXFP4
- Licence
- other
- Downloads
- 42 in the last 30 days · 1.1K all time · 0 likes
- Published
- 2026-01-03 · updated 2026-01-03 (10mo ago)
- Languages
- en
- Tags
- minimax_m2, minimax, MOE, pruning, compression, custom_code