FuseAI · First MLX build 23 Jan 2025
FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview
MLX
apache-2.0
A 33B parameter model from FuseAI, with 3 MLX builds, from 3-bit to 8-bit.
- Parameters
- 33B From Hugging Face
- Quantisation
- 8-bit FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8
- Memory needed
- 41 GB Estimate, unified memory
- Download
- 34.8 GB Weights, estimated
- Downloads
- 774 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 41 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8MLX builds
3 on mlx-community| FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-3bit | 3-bit | 14.3 GB | 19 GB | 639 |
|---|---|---|---|---|
| FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-4bit | 4-bit | 18.4 GB | 23 GB | 66 |
| FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-Q8 | 8-bit | 34.8 GB | 41 GB | 774 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.