deepseek-coder-6.7B-instruct-AWQ is an AWQ-quantized version of DeepSeek's 6.7B coding model, repackaged by TheBloke for Hugging Face. It is specialized for programming tasks and computer science questions. The quantized format enables efficient inference on consumer hardware while retaining strong code generation and instruction-following abilities.
In the Coding AI & assistants space, Deepseek Coder 6.7B Instruct takes a focused approach. It focuses on running a capable coding model locally or in constrained environments using AWQ quantization. Deepseek Coder 6.7B Instruct is an open-source project aimed at developers and AI engineers. The project is open source (AGPL-3.0). Deepseek Coder 6.7B Instruct is available on the web, the command line, and API.
It is developed by TheBloke, and it first shipped in 2022. Development happens publicly on GitHub with 47.5k stars and 141 commits in the last 90 days. PulseGate's similarity index places it among 5 comparable projects. Key capabilities include code generation, AWQ quantization, and instruct-tuned.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do