gpt-oss-20b-Ja-Fin-Thinking-MLX-8bit
mlx-community/gpt-oss-20b-Ja-Fin-Thinking-MLX-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
21B
Weights (est.)
≈ 22.2 GB
Mac memory (est.)
32 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/gpt-oss-20b-Ja-Fin-Thinking-MLX-8bit --prompt "Hello"
Details
- Base model
- nri-ai/gpt-oss-20b-Ja-Fin-Thinking (quantized)
- Vendor
- nri-ai
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 145 in the last 30 days · 1.7K all time · 1 likes
- Published
- 2026-03-27 · updated 2026-03-27 (7mo ago)
- Languages
- ja, en
- Tags
- gpt_oss
Other MLX builds of nri-ai/gpt-oss-20b-Ja-Fin-Thinking
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gpt-oss-20b-Ja-Fin-Thinking-MLX-4bit | 4-bit | ≈ 11.8 GB | 16 GB+ | 167 |
| gpt-oss-20b-Ja-Fin-Thinking-MLX-8bit (this one) | 8-bit | ≈ 22.2 GB | 32 GB+ | 145 |