deepseek-coder-1.3b-base-AWQ
This is an AWQ-quantized version of the DeepSeek Coder 1.3B base model, hosted on Hugging Face and listed in an official community resource collection for efficient local inference.
- Updated
- 2026-06-07
Summary
This is an AWQ-quantized version of the DeepSeek Coder 1.3B base model, hosted on Hugging Face and listed in an official community resource collection for efficient local inference.
The URL points to a Hugging Face model card, a standard platform for hosting and distributing machine learning models.. The source evidence shows it is listed in the 'awesome-deepseek-coder' curated README under 'Quantized Models'.. AWQ (Activation-aware Weight Quantization) is a known technique for efficient model quantization, supporting its utility for deployment.. The model is the 1.3B parameter version, which is suitable for resource-constrained environments or rapid prototyping.