Edit model card


Original Model


Run with LlamaEdge

  • LlamaEdge version: v0.2.15 and above

  • Prompt template

    • Prompt type: chatml

    • Prompt string

  • Context size: 2560

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-4B-Chat-Q5_K_M.gguf llama-api-server.wasm -p chatml
  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-4B-Chat-Q5_K_M.gguf llama-chat.wasm -p chatml

Quantized GGUF Models

Name Quant method Bits Size Use case
Qwen1.5-4B-Chat-Q2_K.gguf Q2_K 2 1.62 GB smallest, significant quality loss - not recommended for most purposes
Qwen1.5-4B-Chat-Q3_K_L.gguf Q3_K_L 3 2.17 GB small, substantial quality loss
Qwen1.5-4B-Chat-Q3_K_M.gguf Q3_K_M 3 2.03 GB very small, high quality loss
Qwen1.5-4B-Chat-Q3_K_S.gguf Q3_K_S 3 1.86 GB very small, high quality loss
Qwen1.5-4B-Chat-Q4_0.gguf Q4_0 4 2.33 GB legacy; small, very high quality loss - prefer using Q3_K_M
Qwen1.5-4B-Chat-Q4_K_M.gguf Q4_K_M 4 2.46 GB medium, balanced quality - recommended
Qwen1.5-4B-Chat-Q4_K_S.gguf Q4_K_S 4 2.34 GB small, greater quality loss
Qwen1.5-4B-Chat-Q5_0.gguf Q5_0 5 2.78 GB legacy; medium, balanced quality - prefer using Q4_K_M
Qwen1.5-4B-Chat-Q5_K_M.gguf Q5_K_M 5 2.84 GB large, very low quality loss - recommended
Qwen1.5-4B-Chat-Q5_K_S.gguf Q5_K_S 5 2.78 GB large, low quality loss - recommended
Qwen1.5-4B-Chat-Q6_K.gguf Q6_K 6 3.25 GB very large, extremely low quality loss
Qwen1.5-4B-Chat-Q8_0.gguf Q8_0 8 4.2 GB very large, extremely low quality loss - not recommended
Downloads last month
Model size
3.95B params

Quantized from