FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8
mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8
Uncategorised · mlx
8-bit Open on Hugging Face
Parameters
33B
Weights (est.)
≈ 34.8 GB
Mac memory (est.)
48 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.
Details
- Base model
- FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview (quantized)
- Vendor
- FuseAI
- Task
- Uncategorised
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 754 in the last 30 days · 8.2K all time · 9 likes
- Published
- 2025-02-19 · updated 2025-02-21 (1y ago)
- Tags
- qwen2, code
Other MLX builds of FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit | 3-bit | ≈ 14.3 GB | 24 GB+ | 610 |
| FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-4bit | 4-bit | ≈ 18.4 GB | 24 GB+ | 59 |
| FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-4.5bit | 5-bit | ≈ 22.5 GB | 32 GB+ | 78 |
| FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8 (this one) | 8-bit | ≈ 34.8 GB | 48 GB+ | 754 |