deepseek-coder-33B-instruct-GPTQ
A GPTQ-quantized version of the DeepSeek-Coder-33B-instruct model hosted on Hugging Face, designed for efficient local inference of a large code-focused language model.
- Updated
- 2026-06-06
Summary
A GPTQ-quantized version of the DeepSeek-Coder-33B-instruct model hosted on Hugging Face, designed for efficient local inference of a large code-focused language model.
Found in the official 'deepseek-ai/awesome-deepseek-coder' repository under 'Community Resources > Quantized Models'.. The URL points to a Hugging Face model repository page, confirming it is a downloadable model artifact.. The filename 'deepseek-coder-33B-instruct-GPTQ' explicitly indicates the model size (33B), variant (instruct), and format (GPTQ).