deepseek-coder-5.7bmqa-instruct-GPTQ
A quantized GPTQ model for DeepSeek Coder 5.7B instruct, hosted on Hugging Face by TheBloke. It provides a ready-to-use, memory-efficient format for local inference of a code-focused instruct model.
- Updated
- 2026-06-06
Summary
A quantized GPTQ model for DeepSeek Coder 5.7B instruct, hosted on Hugging Face by TheBloke. It provides a ready-to-use, memory-efficient format for local inference of a code-focused instruct model.
Found in the official 'awesome-deepseek-coder' README under the 'Quantized Models' section for DeepSeek Coder.. The Hugging Face model card and repository structure are standard for this type of quantized model.. The GPTQ format is a common quantization method for enabling LLM inference on local hardware.