deepseek-coder-1.3b-base-GGUF

A community-provided GGUF quantization of DeepSeek Coder 1.3B base model, hosted on Hugging Face for local inference with tools like llama.cpp. It's a useful but unofficial adaptation of the official model.

Open repository
Updated
2026-06-06

Summary

A community-provided GGUF quantization of DeepSeek Coder 1.3B base model, hosted on Hugging Face for local inference with tools like llama.cpp. It's a useful but unofficial adaptation of the official model.

Listed in the 'Quantized Models' table of the official 'awesome-deepseek-coder' curated README.. Hosted on Hugging Face by user 'TheBloke', a prolific source of quantized models for the LLM community.. The URL and title directly indicate it is a GGUF (quantized) version of the official 'deepseek-coder-1.3b-base' model.

Tags

Also appears in