Alibaba Qwen · First MLX build 6 Jun 2025
Qwen3-Embedding-0.6B
MLX
Text apache-2.0
A 596M parameter text generation model from Alibaba Qwen, with 2 MLX builds, from 4-bit DWQ to 8-bit.
- Parameters
- 596M From Hugging Face
- Quantisation
- 4-bit DWQ Qwen3-Embedding-0.6B-4bit-DWQ
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 335 MB Weights, estimated
- Downloads
- 32K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 4-bit DWQ
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 · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3-Embedding-0.6B-4bit-DWQ --prompt "Hello"MLX builds
2 on mlx-community| Qwen3-Embedding-0.6B-4bit-DWQ | 4-bit DWQ | 335 MB | 3 GB | 32K |
|---|---|---|---|---|
| Qwen3-Embedding-0.6B-8bit | 8-bit | 633 MB | 3 GB | 6.7K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.