README.md

metadata

base_model: Qwen/Qwen3-30B-A3B-Thinking-2507
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507/blob/main/LICENSE
model_creator: Qwen
model_name: Qwen3-30B-A3B-Thinking-2507
quantized_by: Second State Inc.
pipeline_tag: text-generation
library_name: transformers

---

Qwen3-30B-A3B-Thinking-2507-GGUF

Original Model

Qwen/Qwen3-30B-A3B-Thinking-2507

Run with LlamaEdge

• LlamaEdge version: coming soon

• Prompt template

  • Prompt type: chatml

  • Prompt string

    <|im_start|>system
    {system_message}<|im_end|>
    <|im_start|>user
    {prompt}<|im_end|>
    <|im_start|>assistant
    

• Context size: 256000

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-30B-A3B-Thinking-2507-Q5_K_M.gguf \
    llama-api-server.wasm \
    --model-name Qwen3-30B-A3B-Thinking-2507 \
    --prompt-template chatml \
    --ctx-size 256000
  

Quantized with llama.cpp b6031