by ggml-org
Open source · 217k downloads · 9 likes
The Qwen3 Coder 30B A3B Instruct Q8 0 GGUF model is an optimized version of the Qwen3 Coder, specifically designed for local execution through the GGUF format. It excels in generating and understanding code, providing advanced capabilities to assist developers with tasks such as writing, debugging, or explaining programs. Its primary use cases include programming assistance, automation of technical tasks, and code analysis, while ensuring enhanced privacy thanks to its offline operation. This model stands out for its balance between performance and efficiency, enabling smooth operation even on modest hardware configurations.
This model was converted to GGUF format from Qwen/Qwen3-Coder-30B-A3B-Instruct using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Install llama.cpp through brew (works on Mac and Linux)
brew install llama.cpp
Invoke the llama.cpp server or the CLI.
llama-cli --hf-repo ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF --hf-file qwen3-coder-30b-a3b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
llama-server --hf-repo ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF --hf-file qwen3-coder-30b-a3b-instruct-q8_0.gguf -c 2048
Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
git clone https://github.com/ggml-org/llama.cpp
Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
cd llama.cpp && LLAMA_CURL=1 make
Step 3: Run inference through the main binary.
./llama-cli --hf-repo ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF --hf-file qwen3-coder-30b-a3b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
or
./llama-server --hf-repo ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF --hf-file qwen3-coder-30b-a3b-instruct-q8_0.gguf -c 2048