MXFP4 Open on Hugging Face
Parameters
123B
Weights (est.)
≈ 78.4 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/AREX-Base-mixed-mxfp4-bf16 --prompt "Hello"
Details
- Base model
- BAAI/AREX-Base (quantized)
- Vendor
- BAAI
- Task
- Text generation
- Quantisation
- MXFP4
- Licence
- apache-2.0
- Downloads
- 44 in the last 30 days · 194 all time · 0 likes
- Published
- 2026-07-29 · updated 2026-07-29 (3mo ago)
- Languages
- en
- Tags
- qwen3_5_moe, agent, deep-research, reasoning, tool-use, long-context, qwen3.5, mixture-of-experts