4-bit Open on Hugging Face
Parameters
33B
Weights (est.)
≈ 18.8 GB
Mac memory (est.)
24 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-coder-33b-instruct --prompt "Hello"
Details
- Base model
- deepseek-ai/deepseek-coder-33b-instruct (quantized)
- Vendor
- DeepSeek
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- deepseek
- Downloads
- 194 in the last 30 days · 3.7K all time · 2 likes
- Published
- 2025-06-21 · updated 2025-06-21 (1y ago)
- Tags
- llama