4-bit DWQ Open on Hugging Face
Parameters
596M
Weights (est.)
≈ 335 MB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Qwen3-Embedding-0.6B-4bit-DWQ --prompt "Hello"
Details
- Base model
- Qwen/Qwen3-Embedding-0.6B (quantized)
- Vendor
- Qwen
- Task
- Text generation
- Quantisation
- 4-bit DWQ
- Licence
- apache-2.0
- Downloads
- 32K in the last 30 days · 328K all time · 15 likes
- Published
- 2025-06-06 · updated 2025-06-06 (1y ago)
- Tags
- qwen3, sentence-transformers, sentence-similarity, feature-extraction
Other MLX builds of Qwen/Qwen3-Embedding-0.6B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-Embedding-0.6B-4bit-DWQ (this one) | 4-bit DWQ | ≈ 335 MB | 8 GB+ | 32K |
| Qwen3-Embedding-0.6B-8bit | 8-bit | ≈ 633 MB | 8 GB+ | 6.7K |
| ACE-Step-1.5-text-encoder-bf16 | bf16 | ≈ 1.2 GB | 8 GB+ | 149 |