deepseek-coder-33B-base-GPTQ
This is a GPTQ-quantized version of the 33B-base DeepSeek Coder model, hosted on Hugging Face. It is relevant for users looking to run a large coding model efficiently on consumer-grade hardware or with limited VRAM.
- Updated
- 2026-06-06
Summary
This is a GPTQ-quantized version of the 33B-base DeepSeek Coder model, hosted on Hugging Face. It is relevant for users looking to run a large coding model efficiently on consumer-grade hardware or with limited VRAM.
The candidate URL is a Hugging Face model card for 'deepseek-coder-33B-base-GPTQ' by user TheBloke.. The source evidence shows it is listed in the official 'awesome-deepseek-coder' README under 'Community Resources' and 'Quantized Models'.. The title and tags explicitly reference the model architecture (33B), base variant, and quantization method (GPTQ).