Alibaba Qwen · First MLX build 14 Jun 2024
Qwen2-0.5B
MLX
apache-2.0
A 139M parameter model from Alibaba Qwen, with 3 MLX builds, from 2-bit to 8-bit.
- Parameters
- 139M From Hugging Face
- Quantisation
- 4-bit dolphin-2.9.3-qwen2-0.5b-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 66 MB Weights, estimated
- Downloads
- 127 This build, last 30 days
- Task
- —
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 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/dolphin-2.9.3-qwen2-0.5b-4bitMLX builds
3 on mlx-community| dolphin-2.9.3-qwen2-0.5b-2bit | 2-bit | 41 MB | 3 GB | 34 |
|---|---|---|---|---|
| dolphin-2.9.3-qwen2-0.5b-4bit | 4-bit | 66 MB | 3 GB | 127 |
| dolphin-2.9.3-qwen2-0.5b-8bit | 8-bit | 162 MB | 3 GB | 27 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.