---

stablelm-2-12b-chat-GGUF

Original Model

stabilityai/stablelm-2-12b-chat

Run with LlamaEdge

• LlamaEdge version: v0.12.2 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:stablelm-2-12b-chat-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template chatml \
    --ctx-size 4096 \
    --model-name stablelm-2-12b-chat
  

• Run as LlamaEdge command app

  wasmedge --dir .:. \
    --nn-preload default:GGML:AUTO:stablelm-2-12b-chat-Q5_K_M.gguf \
    llama-chat.wasm \
    --prompt-template chatml \
    --ctx-size 4096
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
stablelm-2-12b-chat-Q2_K.gguf	Q2_K	2	4.70 GB	smallest, significant quality loss - not recommended for most purposes
stablelm-2-12b-chat-Q3_K_L.gguf	Q3_K_L	3	6.49 GB	small, substantial quality loss
stablelm-2-12b-chat-Q3_K_M.gguf	Q3_K_M	3	5.99 GB	very small, high quality loss
stablelm-2-12b-chat-Q3_K_S.gguf	Q3_K_S	3	5.42 GB	very small, high quality loss
stablelm-2-12b-chat-Q4_0.gguf	Q4_0	4	6.97 GB	legacy; small, very high quality loss - prefer using Q3_K_M
stablelm-2-12b-chat-Q4_K_M.gguf	Q4_K_M	4	7.37 GB	medium, balanced quality - recommended
stablelm-2-12b-chat-Q4_K_S.gguf	Q4_K_S	4	7.02 GB	small, greater quality loss
stablelm-2-12b-chat-Q5_0.gguf	Q5_0	5	8.42 GB	legacy; medium, balanced quality - prefer using Q4_K_M
stablelm-2-12b-chat-Q5_K_M.gguf	Q5_K_M	5	8.63 GB	large, very low quality loss - recommended
stablelm-2-12b-chat-Q5_K_S.gguf	Q5_K_S	5	8.42 GB	large, low quality loss - recommended
stablelm-2-12b-chat-Q6_K.gguf	Q6_K	6	9.97 GB	very large, extremely low quality loss
stablelm-2-12b-chat-Q8_0.gguf	Q8_0	8	12.9 GB	very large, extremely low quality loss - not recommended
stablelm-2-12b-chat-f16.gguf	f16	16	24.3 GB

Quantized with llama.cpp b3333