Koitenshin/Qwen3-30B-A3B-ThinkCode-Linear-FP32-GGUF

I've tested the Q4_K_M version on both LM Studio & KoboldCPP, but I can't test the higher quants. It's not very good, but you may have better luck than I did depending on your use case.

This model was converted to GGUF format from BennyDaBall/Qwen3-30B-A3B-ThinkCode-Linear-FP32 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Koitenshin/Qwen3-30B-A3B-ThinkCode-Linear-FP32-Q8_0-GGUF --hf-file qwen3-30b-a3b-thinkcode-linear-fp32-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Koitenshin/Qwen3-30B-A3B-ThinkCode-Linear-FP32-Q8_0-GGUF --hf-file qwen3-30b-a3b-thinkcode-linear-fp32-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/ggerganov/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 Koitenshin/Qwen3-30B-A3B-ThinkCode-Linear-FP32-Q8_0-GGUF --hf-file qwen3-30b-a3b-thinkcode-linear-fp32-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Koitenshin/Qwen3-30B-A3B-ThinkCode-Linear-FP32-Q8_0-GGUF --hf-file qwen3-30b-a3b-thinkcode-linear-fp32-q8_0.gguf -c 2048