README.md

metadata

base_model: Qwen/Qwen3-32B
license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE
model_creator: Qwen
model_name: Qwen3-32B
quantized_by: Second State Inc.

---

Qwen3-32B-GGUF

Original Model

Qwen/Qwen3-32B

Run with LlamaEdge

• LlamaEdge version:

  • Thinking: v0.17.0 and above
  • No Thinking: v0.18.2

• Prompt template

  • Prompt type: chatml (for thinking)

  • Prompt string

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

  • Prompt type: qwen3-no-think (for no thinking)

  • Prompt string

    <|im_start|>system
    {system_message}<|im_end|>
    <|im_start|>user
    {user_message_1}<|im_end|>
    <|im_start|>assistant
    {assistant_message_1}<|im_end|>
    <|im_start|>user
    {user_message_2}<|im_end|>
    <|im_start|>assistant
    <think>
    
    </think>
    

• Context size: 128000

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen3-32B-Q5_K_M.gguf \
    llama-api-server.wasm \
    --model-name Qwen3-32B \
    --prompt-template chatml \
    --ctx-size 128000
  

Quantized with llama.cpp b5097