---

Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF

Original Model

NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT

Run with LlamaEdge

• LlamaEdge version: v0.2.8 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: 4096

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_M.gguf llama-api-server.wasm -p chatml
  

• Run as LlamaEdge command app

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_M.gguf llama-chat.wasm -p chatml
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Nous-Hermes-2-Mixtral-8x7B-SFT-Q2_K.gguf	Q2_K	2	17.3 GB	smallest, significant quality loss - not recommended for most purposes
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_L.gguf	Q3_K_L	3	24.2 GB	small, substantial quality loss
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_M.gguf	Q3_K_M	3	22.5 GB	very small, high quality loss
Nous-Hermes-2-Mixtral-8x7B-SFT-Q3_K_S.gguf	Q3_K_S	3	20.4 GB	very small, high quality loss
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_0.gguf	Q4_0	4	26.4 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_M.gguf	Q4_K_M	4	28.4 GB	medium, balanced quality - recommended
Nous-Hermes-2-Mixtral-8x7B-SFT-Q4_K_S.gguf	Q4_K_S	4	26.7 GB	small, greater quality loss
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_0.gguf	Q5_0	5	32.2 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_M.gguf	Q5_K_M	5	33.2 GB	large, very low quality loss - recommended
Nous-Hermes-2-Mixtral-8x7B-SFT-Q5_K_S.gguf	Q5_K_S	5	32.2 GB	large, low quality loss - recommended
Nous-Hermes-2-Mixtral-8x7B-SFT-Q6_K.gguf	Q6_K	6	38.4 GB	very large, extremely low quality loss
Nous-Hermes-2-Mixtral-8x7B-SFT-Q8_0.gguf	Q8_0	8	49.6 GB	very large, extremely low quality loss - not recommended