Orion-zhen · First MLX build 29 Jan 2025
DeepSeek-R1-Distill-Qwen-7B-abliterated
MLX
gpl-3.0
A 7.6B parameter model from Orion-zhen, with one MLX build at 4-bit.
- Parameters
- 7.6B From Hugging Face
- Quantisation
- 4-bit DeepSeek-R1-Distill-Qwen-7B-abliterated-4bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.3 GB Weights, estimated
- Downloads
- 156 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 7 GB at 4-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/DeepSeek-R1-Distill-Qwen-7B-abliterated-4bitMLX builds
1 on mlx-community| DeepSeek-R1-Distill-Qwen-7B-abliterated-4bit | 4-bit | 4.3 GB | 7 GB | 156 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.