Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit
mlx-community/Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
15B
Weights (est.)
≈ 8.3 GB
Mac memory (est.)
16 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/Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit --prompt "Hello"
Details
- Base model
- nri-ai/Qwen3-14B-Ja-Fin-Thinking (quantized)
- Vendor
- nri-ai
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 77 in the last 30 days · 389 all time · 0 likes
- Published
- 2026-03-27 · updated 2026-03-27 (7mo ago)
- Languages
- ja, en
- Tags
- qwen3
Other MLX builds of nri-ai/Qwen3-14B-Ja-Fin-Thinking
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit (this one) | 4-bit | ≈ 8.3 GB | 16 GB+ | 77 |
| Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-8bit | 8-bit | ≈ 15.7 GB | 24 GB+ | 81 |