---

Qwen1.5-7B-Chat-GGUF

Original Model

Qwen/Qwen1.5-7B-Chat

Run with LlamaEdge

• LlamaEdge version: v0.2.15 and above

• 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: 32000

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-7B-Chat-Q5_K_M.gguf llama-api-server.wasm -p chatml
  

• Run as LlamaEdge command app

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-7B-Chat-Q5_K_M.gguf llama-chat.wasm -p chatml
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Qwen1.5-7B-Chat-Q2_K.gguf	Q2_K	2	3.10 GB	smallest, significant quality loss - not recommended for most purposes
Qwen1.5-7B-Chat-Q3_K_L.gguf	Q3_K_L	3	4.22 GB	small, substantial quality loss
Qwen1.5-7B-Chat-Q3_K_M.gguf	Q3_K_M	3	3.92 GB	very small, high quality loss
Qwen1.5-7B-Chat-Q3_K_S.gguf	Q3_K_S	3	3.57 GB	very small, high quality loss
Qwen1.5-7B-Chat-Q4_0.gguf	Q4_0	4	4.51 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Qwen1.5-7B-Chat-Q4_K_M.gguf	Q4_K_M	4	4.77 GB	medium, balanced quality - recommended
Qwen1.5-7B-Chat-Q4_K_S.gguf	Q4_K_S	4	4.54 GB	small, greater quality loss
Qwen1.5-7B-Chat-Q5_0.gguf	Q5_0	5	5.40 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Qwen1.5-7B-Chat-Q5_K_M.gguf	Q5_K_M	5	5.53 GB	large, very low quality loss - recommended
Qwen1.5-7B-Chat-Q5_K_S.gguf	Q5_K_S	5	5.4 GB	large, low quality loss - recommended
Qwen1.5-7B-Chat-Q6_K.gguf	Q6_K	6	6.34 GB	very large, extremely low quality loss
Qwen1.5-7B-Chat-Q8_0.gguf	Q8_0	8	8.21 GB	very large, extremely low quality loss - not recommended