deepseek-coder-6.7B-instruct-GGUF
This is a community-hosted GGUF quantization of DeepSeek Coder 6.7B Instruct, optimized for local inference via tools like llama.cpp. It is a practical, lightweight resource for developers wanting to run the model efficiently on consumer hardware.
- Updated
- 2026-06-06
Summary
This is a community-hosted GGUF quantization of DeepSeek Coder 6.7B Instruct, optimized for local inference via tools like llama.cpp. It is a practical, lightweight resource for developers wanting to run the model efficiently on consumer hardware.
Sourced from the official 'deepseek-ai/awesome-deepseek-coder' README under the 'Community Resources > Quantized Models' section.. The Hugging Face repository page title explicitly states it is a GGUF quantization of the instruct model.. GGUF is the standard format for llama.cpp, confirming its practical deployment use case.