Alibaba Qwen · First MLX build 8 Jun 2025
Qwen3-Embedding-8B
MLX
Text apache-2.0
A 7.6B parameter embeddings model from Alibaba Qwen, with one MLX build at 4-bit DWQ.
- Parameters
- 7.6B From Hugging Face
- Quantisation
- 4-bit DWQ Qwen3-Embedding-8B-4bit-DWQ
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.3 GB Weights, estimated
- Downloads
- 2.6K This build, last 30 days
- Task
- Embeddings Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 7 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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Qwen3-Embedding-8B-4bit-DWQMLX builds
1 on mlx-community| Qwen3-Embedding-8B-4bit-DWQ | 4-bit DWQ | 4.3 GB | 7 GB | 2.6K |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.