Deductive-Reasoning-Qwen-32B-MLX-4bit
mlx-community/Deductive-Reasoning-Qwen-32B-MLX-4bit
Text generation · transformers
4-bit Open on Hugging Face
Parameters
33B
Weights (est.)
≈ 18.4 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/Deductive-Reasoning-Qwen-32B-MLX-4bit --prompt "Hello"
Details
- Base model
- OpenPipe/Deductive-Reasoning-Qwen-32B (quantized)
- Vendor
- OpenPipe
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 33 in the last 30 days · 260 all time · 1 likes
- Published
- 2025-03-11 · updated 2025-03-11 (1y ago)
- Languages
- en
- Tags
- qwen2, chat
Other MLX builds of OpenPipe/Deductive-Reasoning-Qwen-32B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Deductive-Reasoning-Qwen-32B-MLX-4bit (this one) | 4-bit | ≈ 18.4 GB | 24 GB+ | 33 |
| Deductive-Reasoning-Qwen-32B-MLX-6bit | 6-bit | ≈ 26.6 GB | 32 GB+ | 46 |
| Deductive-Reasoning-Qwen-32B-MLX-8bit | 8-bit | ≈ 34.8 GB | 48 GB+ | 27 |