MXFP4 Open on Hugging Face
Parameters
21B
Weights (est.)
≈ 14.4 GB
Mac memory (est.)
24 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/Jinx-gpt-oss-20b-mxfp4-mlx --prompt "Hello"
Details
- Base model
- Jinx-org/Jinx-gpt-oss-20b-mxfp4 (quantized)
- Vendor
- Jinx-org
- Task
- Text generation
- Quantisation
- MXFP4
- Licence
- apache-2.0
- Downloads
- 164 in the last 30 days · 2.7K all time · 4 likes
- Published
- 2025-09-17 · updated 2025-09-17 (1y ago)
- Tags
- gpt_oss, vllm