Qwen3-30B-A3B-GGUF

<!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end -->

Qwen3-30B-A3B-GGUF

Original Model

Qwen/Qwen3-30B-A3B

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:Qwen3-30B-A3B-Q5_K_M.gguf \
    llama-api-server.wasm \
    --model-name Qwen3-30B-A3B \
    --prompt-template chatml \
    --ctx-size 128000
  

<!-- ## Quantized GGUF Models | Name | Quant method | Bits | Size | Use case | | ---- | ---- | ---- | ---- | ----- | | [Qwen3-30B-A3B-Q2_K.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q2_K.gguf) | Q2_K | 2 | 3.28 GB| smallest, significant quality loss - not recommended for most purposes | | [Qwen3-30B-A3B-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.43 GB| small, substantial quality loss | | [Qwen3-30B-A3B-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q3_K_M.gguf) | Q3_K_M | 3 | 4.12 GB| very small, high quality loss | | [Qwen3-30B-A3B-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.77 GB| very small, high quality loss | | [Qwen3-30B-A3B-Q4_0.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q4_0.gguf) | Q4_0 | 4 | 4.77 GB| legacy; small, very high quality loss - prefer using Q3_K_M | | [Qwen3-30B-A3B-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q4_K_M.gguf) | Q4_K_M | 4 | 5.03 GB| medium, balanced quality - recommended | | [Qwen3-30B-A3B-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.80 GB| small, greater quality loss | | [Qwen3-30B-A3B-Q5_0.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q5_0.gguf) | Q5_0 | 5 | 5.72 GB| legacy; medium, balanced quality - prefer using Q4_K_M | | [Qwen3-30B-A3B-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.85 GB| large, very low quality loss - recommended | | [Qwen3-30B-A3B-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.72 GB| large, low quality loss - recommended | | [Qwen3-30B-A3B-Q6_K.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q6_K.gguf) | Q6_K | 6 | 6.73 GB| very large, extremely low quality loss | | [Qwen3-30B-A3B-Q8_0.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-Q8_0.gguf) | Q8_0 | 8 | 8.71 GB| very large, extremely low quality loss - not recommended | | [Qwen3-30B-A3B-f16.gguf](https://huggingface.co/second-state/Qwen3-30B-A3B-GGUF/blob/main/Qwen3-30B-A3B-f16.gguf) | f16 | 16 | 16.4 GB| | -->

Quantized with llama.cpp b5097