base_model, inference, license, license_link, license_name, model_creator, model_name, model_type, quantized_by

base_model	inference	license	license_link	license_name	model_creator	model_name	model_type	quantized_by
deepseek-ai/deepseek-coder-6.7b-instruct	false	other	LICENSE	deepseek	DeepSeek	Deepseek Coder 6.7B Instruct	deepseek	Second State Inc.

---

Deepseek-Coder-6.7B-Instruct-GGUF

Original Model

deepseek-ai/deepseek-coder-6.7b-instruct

Run with LlamaEdge

• LlamaEdge version: v0.2.8 and above

• Prompt template

  • Prompt type: deepseek-coder

  • Prompt string

    {system}
    \### Instruction:
    {question_1}
    \### Response:
    {answer_1}
    <|EOT|>
    \### Instruction:
    {question_2}
    \### Response:
    

    Note that the \ character is used to escape the ### in the prompt string. Remove it in the practical use.

• Context size: 4096

• Run as LlamaEdge service

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:deepseek-coder-6.7b-instruct-Q5_K_M.gguf llama-api-server.wasm -p deepseek-coder
  

• Run as LlamaEdge command app

  wasmedge --dir .:. --nn-preload default:GGML:AUTO:deepseek-coder-6.7b-instruct-Q5_K_M.gguf llama-chat.wasm -p deepseek-coder
  

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
deepseek-coder-6.7b-instruct-Q2_K.gguf	Q2_K	2	2.53 GB	smallest, significant quality loss - not recommended for most purposes
deepseek-coder-6.7b-instruct-Q3_K_L.gguf	Q3_K_L	3	3.6 GB	small, substantial quality loss
deepseek-coder-6.7b-instruct-Q3_K_M.gguf	Q3_K_M	3	3.3 GB	very small, high quality loss
deepseek-coder-6.7b-instruct-Q3_K_S.gguf	Q3_K_S	3	2.95 GB	very small, high quality loss
deepseek-coder-6.7b-instruct-Q4_0.gguf	Q4_0	4	3.83 GB	legacy; small, very high quality loss - prefer using Q3_K_M
deepseek-coder-6.7b-instruct-Q4_K_M.gguf	Q4_K_M	4	4.08 GB	medium, balanced quality - recommended
deepseek-coder-6.7b-instruct-Q4_K_S.gguf	Q4_K_S	4	3.86 GB	small, greater quality loss
deepseek-coder-6.7b-instruct-Q5_0.gguf	Q5_0	5	4.65 GB	legacy; medium, balanced quality - prefer using Q4_K_M
deepseek-coder-6.7b-instruct-Q5_K_M.gguf	Q5_K_M	5	4.79 GB	large, very low quality loss - recommended
deepseek-coder-6.7b-instruct-Q5_K_S.gguf	Q5_K_S	5	4.65 GB	large, low quality loss - recommended
deepseek-coder-6.7b-instruct-Q6_K.gguf	Q6_K	6	5.53 GB	very large, extremely low quality loss
deepseek-coder-6.7b-instruct-Q8_0.gguf	Q8_0	8	7.16 GB	very large, extremely low quality loss - not recommended