Edit model card

Qwen1.5-1.8B-Chat-GGUF

Original Model

Qwen/Qwen1.5-1.8B-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:Qwen1.5-1.8B-Chat-Q5_K_M.gguf llama-api-server.wasm -p chatml
    
  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen1.5-1.8B-Chat-Q5_K_M.gguf llama-chat.wasm -p chatml
    

Quantized GGUF Models

Name Quant method Bits Size Use case
Qwen1.5-1.8B-Chat-Q2_K.gguf Q2_K 2 863 MB smallest, significant quality loss - not recommended for most purposes
Qwen1.5-1.8B-Chat-Q3_K_L.gguf Q3_K_L 3 1.06 GB small, substantial quality loss
Qwen1.5-1.8B-Chat-Q3_K_M.gguf Q3_K_M 3 1.02 GB very small, high quality loss
Qwen1.5-1.8B-Chat-Q3_K_S.gguf Q3_K_S 3 970 MB very small, high quality loss
Qwen1.5-1.8B-Chat-Q4_0.gguf Q4_0 4 1.12 GB legacy; small, very high quality loss - prefer using Q3_K_M
Qwen1.5-1.8B-Chat-Q4_K_M.gguf Q4_K_M 4 1.22 GB medium, balanced quality - recommended
Qwen1.5-1.8B-Chat-Q4_K_S.gguf Q4_K_S 4 1.16 GB small, greater quality loss
Qwen1.5-1.8B-Chat-Q5_0.gguf Q5_0 5 1.31 GB legacy; medium, balanced quality - prefer using Q4_K_M
Qwen1.5-1.8B-Chat-Q5_K_M.gguf Q5_K_M 5 1.38 GB large, very low quality loss - recommended
Qwen1.5-1.8B-Chat-Q5_K_S.gguf Q5_K_S 5 1.33 GB large, low quality loss - recommended
Qwen1.5-1.8B-Chat-Q6_K.gguf Q6_K 6 1.58 GB very large, extremely low quality loss
Qwen1.5-1.8B-Chat-Q8_0.gguf Q8_0 8 1.96 GB very large, extremely low quality loss - not recommended
Downloads last month
705
GGUF
Model size
1.84B params
Architecture
qwen2

Quantized from