---

Gemma-2-9B-Chinese-Chat-GGUF

Original Model

shenzhi-wang/Gemma-2-9B-Chinese-Chat

Run with LlamaEdge

• LlamaEdge version: v0.12.1 and above

• Prompt template

  • Prompt type: gemma-instruct

  • Prompt string

    <bos><start_of_turn>user
    {user_message}<end_of_turn>
    <start_of_turn>model
    {model_message}<end_of_turn>model
    

• Context size: 8192

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template gemma-instruct \
    --ctx-size 8192 \
    --model-name gemma-2-9b
  

• Run as LlamaEdge command app

  wasmedge --dir .:. \
    --nn-preload default:GGML:AUTO:Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template gemma-instruct \
    --ctx-size 8192
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Gemma-2-9B-Chinese-Chat-Q2_K.gguf	Q2_K	2	3.81 GB	smallest, significant quality loss - not recommended for most purposes
Gemma-2-9B-Chinese-Chat-Q3_K_L.gguf	Q3_K_L	3	5.13 GB	small, substantial quality loss
Gemma-2-9B-Chinese-Chat-Q3_K_M.gguf	Q3_K_M	3	4.76 GB	very small, high quality loss
Gemma-2-9B-Chinese-Chat-Q3_K_S.gguf	Q3_K_S	3	4.34 GB	very small, high quality loss
Gemma-2-9B-Chinese-Chat-Q4_0.gguf	Q4_0	4	5.44 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Gemma-2-9B-Chinese-Chat-Q4_K_M.gguf	Q4_K_M	4	5.76 GB	medium, balanced quality - recommended
Gemma-2-9B-Chinese-Chat-Q4_K_S.gguf	Q4_K_S	4	5.48 GB	small, greater quality loss
Gemma-2-9B-Chinese-Chat-Q5_0.gguf	Q5_0	5	6.48 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Gemma-2-9B-Chinese-Chat-Q5_K_M.gguf	Q5_K_M	5	6.65 GB	large, very low quality loss - recommended
Gemma-2-9B-Chinese-Chat-Q5_K_S.gguf	Q5_K_S	5	6.48 GB	large, low quality loss - recommended
Gemma-2-9B-Chinese-Chat-Q6_K.gguf	Q6_K	6	7.59 GB	very large, extremely low quality loss
Gemma-2-9B-Chinese-Chat-Q8_0.gguf	Q8_0	8	9.83 GB	very large, extremely low quality loss - not recommended
Gemma-2-9B-Chinese-Chat-f16.gguf	f16	16	18.5 GB

Quantized with llama.cpp b3259