Qwen3-Coder-30B-A3B-Instruct

Run with https://llama.app

llama serve -hf ggml-org/Qwen3-Coder-30B-A3B-Instruct-GGUF

Source models

• https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct

Notes

• Ships BF16, Q8_0 and Q4_K_M.
• 30B MoE (3B active), 48 layers, 128 routed experts with 8 active per token, 262K context.
• Q8_0 and Q4_K_M: the routed experts use the base quantization type.
• In Q4_K_M the small non-expert tensors (embeddings, attention) are kept at Q8_0.

TODOs

• add info

[!IMPORTANT] This model is automatically converted using https://github.com/ggml-org/convert