DeepSeek-R1-Qwen3-0528-8B-4bit-AWQ
mlx-community/DeepSeek-R1-Qwen3-0528-8B-4bit-AWQ
Text generation · mlx
4-bit Open on Hugging Face
Parameters
8.2B
Weights (est.)
≈ 4.6 GB
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/DeepSeek-R1-Qwen3-0528-8B-4bit-AWQ --prompt "Hello"
Details
- Base model
- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B (finetune)
- Vendor
- DeepSeek
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mit
- Downloads
- 113 in the last 30 days · 14K all time · 4 likes
- Published
- 2025-06-29 · updated 2025-06-29 (1y ago)
- Tags
- qwen3
Other MLX builds of deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| DeepSeek-R1-0528-Qwen3-8B-4bit | 4-bit | ≈ 4.6 GB | 8 GB+ | 3.2K |
| DeepSeek-R1-0528-Qwen3-8B-4bit-DWQ | 4-bit DWQ | ≈ 4.6 GB | 8 GB+ | 137 |
| DeepSeek-R1-Qwen3-0528-8B-4bit-AWQ (this one) | 4-bit | ≈ 4.6 GB | 8 GB+ | 113 |
| DeepSeek-R1-0528-Qwen3-8B-6bit | 6-bit | ≈ 6.7 GB | 16 GB+ | 95 |