Edit model card

DeepSeek-Coder-V2-Instruct-GGUF

Original Model

deepseek-ai/DeepSeek-Coder-V2-Instruct

Run with LlamaEdge

  • LlamaEdge version: v0.12.3 and above

  • Prompt template

    • Prompt type: deepseek-chat-2

    • Prompt string

      <|begin_of_sentence|>{system_message}
      
      User: {user_message_1}
      
      Assistant: {assistant_message_1}<|end_of_sentence|>User: {user_message_2}
      
      Assistant:
      
  • Context size: 128000

  • Run as LlamaEdge service

    wasmedge --dir .:. \
      --nn-preload default:GGML:AUTO:DeepSeek-Coder-V2-Instruct-Q5_K_M.gguf \
      llama-api-server.wasm \
      --prompt-template deepseek-chat-2 \
      --ctx-size 128000 \
      --model-name DeepSeek-Coder-V2-Instruct
    
  • Run as LlamaEdge command app

    wasmedge --dir .:. \
      --nn-preload default:GGML:AUTO:DeepSeek-Coder-V2-Instruct-Q5_K_M.gguf \
      llama-chat.wasm \
      --prompt-template deepseek-chat-2 \
      --ctx-size 128000
    

Quantized GGUF Models

Name Quant method Bits Size Use case
DeepSeek-Coder-V2-Instruct-Q2_K-00001-of-00003.gguf Q2_K 2 29.7 GB smallest, significant quality loss - not recommended for most purposes
DeepSeek-Coder-V2-Instruct-Q2_K-00002-of-00003.gguf Q2_K 2 29.8 GB smallest, significant quality loss - not recommended for most purposes
DeepSeek-Coder-V2-Instruct-Q2_K-00002-of-00003.gguf Q2_K 2 26.4 GB smallest, significant quality loss - not recommended for most purposes
DeepSeek-Coder-V2-Instruct-Q3_K_L-00001-of-00005.gguf Q3_K_L 3 29.8 GB small, substantial quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_L-00002-of-00005.gguf Q3_K_L 3 29.7 GB small, substantial quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_L-00003-of-00005.gguf Q3_K_L 3 29.9 GB small, substantial quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_L-00004-of-00005.gguf Q3_K_L 3 29.8 GB small, substantial quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_L-00005-of-00005.gguf Q3_K_L 3 3.14 GB small, substantial quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_M-00001-of-00004.gguf Q3_K_M 3 29.6 GB very small, high quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_M-00002-of-00004.gguf Q3_K_M 3 29.5 GB very small, high quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_M-00003-of-00004.gguf Q3_K_M 3 29.8 GB very small, high quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_M-00004-of-00004.gguf Q3_K_M 3 23.8 GB very small, high quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_S-00001-of-00004.gguf Q3_K_S 3 29.9 GB very small, high quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_S-00002-of-00004.gguf Q3_K_S 3 29.7 GB very small, high quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_S-00003-of-00004.gguf Q3_K_S 3 29.6 GB very small, high quality loss
DeepSeek-Coder-V2-Instruct-Q3_K_S-00004-of-00004.gguf Q3_K_S 3 12.5 GB very small, high quality loss
DeepSeek-Coder-V2-Instruct-Q4_0-00001-of-00005.gguf Q4_0 4 30.0 GB legacy; small, very high quality loss - prefer using Q3_K_M
DeepSeek-Coder-V2-Instruct-Q4_0-00002-of-00005.gguf Q4_0 4 29.9 GB legacy; small, very high quality loss - prefer using Q3_K_M
DeepSeek-Coder-V2-Instruct-Q4_0-00003-of-00005.gguf Q4_0 4 29.8 GB legacy; small, very high quality loss - prefer using Q3_K_M
DeepSeek-Coder-V2-Instruct-Q4_0-00004-of-00005.gguf Q4_0 4 29.9 GB legacy; small, very high quality loss - prefer using Q3_K_M
DeepSeek-Coder-V2-Instruct-Q4_0-00005-of-00005.gguf Q4_0 4 13.3 GB legacy; small, very high quality loss - prefer using Q3_K_M
DeepSeek-Coder-V2-Instruct-Q4_K_M-00001-of-00005.gguf Q4_K_M 4 29.7 GB medium, balanced quality - recommended
DeepSeek-Coder-V2-Instruct-Q4_K_M-00002-of-00005.gguf Q4_K_M 4 29.7 GB medium, balanced quality - recommended
DeepSeek-Coder-V2-Instruct-Q4_K_M-00003-of-00005.gguf Q4_K_M 4 29.7 GB medium, balanced quality - recommended
DeepSeek-Coder-V2-Instruct-Q4_K_M-00004-of-00005.gguf Q4_K_M 4 29.6 GB medium, balanced quality - recommended
DeepSeek-Coder-V2-Instruct-Q4_K_M-00005-of-00005.gguf Q4_K_M 4 23.8 GB medium, balanced quality - recommended
DeepSeek-Coder-V2-Instruct-Q4_K_S-00001-of-00005.gguf Q4_K_S 4 29.6 GB small, greater quality loss
DeepSeek-Coder-V2-Instruct-Q4_K_S-00002-of-00005.gguf Q4_K_S 4 29.8 GB small, greater quality loss
DeepSeek-Coder-V2-Instruct-Q4_K_S-00003-of-00005.gguf Q4_K_S 4 29.9 GB small, greater quality loss
DeepSeek-Coder-V2-Instruct-Q4_K_S-00004-of-00005.gguf Q4_K_S 4 29.8 GB small, greater quality loss
DeepSeek-Coder-V2-Instruct-Q4_K_S-00005-of-00005.gguf Q4_K_S 4 14.8 GB small, greater quality loss
DeepSeek-Coder-V2-Instruct-Q5_0-00001-of-00006.gguf Q5_0 5 29.4 GB legacy; medium, balanced quality - prefer using Q4_K_M
DeepSeek-Coder-V2-Instruct-Q5_0-00002-of-00006.gguf Q5_0 5 29.2 GB legacy; medium, balanced quality - prefer using Q4_K_M
DeepSeek-Coder-V2-Instruct-Q5_0-00003-of-00006.gguf Q5_0 5 30.0 GB legacy; medium, balanced quality - prefer using Q4_K_M
DeepSeek-Coder-V2-Instruct-Q5_0-00004-of-00006.gguf Q5_0 5 29.2 GB legacy; medium, balanced quality - prefer using Q4_K_M
DeepSeek-Coder-V2-Instruct-Q5_0-00005-of-00006.gguf Q5_0 5 29.2 GB legacy; medium, balanced quality - prefer using Q4_K_M
DeepSeek-Coder-V2-Instruct-Q5_0-00006-of-00006.gguf Q5_0 5 15.4 GB legacy; medium, balanced quality - prefer using Q4_K_M
DeepSeek-Coder-V2-Instruct-Q5_K_M-00001-of-00006.gguf Q5_K_M 5 29.7 GB large, very low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_M-00002-of-00006.gguf Q5_K_M 5 29.7 GB large, very low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_M-00003-of-00006.gguf Q5_K_M 5 29.7 GB large, very low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_M-00004-of-00006.gguf Q5_K_M 5 29.9 GB large, very low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_M-00005-of-00006.gguf Q5_K_M 5 29.9 GB large, very low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_M-00006-of-00006.gguf Q5_K_M 5 18.3 GB large, very low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_S-00001-of-00006.gguf Q5_K_S 5 29.4 GB large, low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_S-00002-of-00006.gguf Q5_K_S 5 29.2 GB large, low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_S-00003-of-00006.gguf Q5_K_S 5 30.0 GB large, low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_S-00004-of-00006.gguf Q5_K_S 5 29.2 GB large, low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_S-00005-of-00006.gguf Q5_K_S 5 29.2 GB large, low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q5_K_S-00006-of-00006.gguf Q5_K_S 5 15.4 GB large, low quality loss - recommended
DeepSeek-Coder-V2-Instruct-Q6_K-00001-of-00007.gguf Q6_K 6 29.6 GB very large, extremely low quality loss
DeepSeek-Coder-V2-Instruct-Q6_K-00002-of-00007.gguf Q6_K 6 29.0 GB very large, extremely low quality loss
DeepSeek-Coder-V2-Instruct-Q6_K-00003-of-00007.gguf Q6_K 6 29.5 GB very large, extremely low quality loss
DeepSeek-Coder-V2-Instruct-Q6_K-00004-of-00007.gguf Q6_K 6 29.3 GB very large, extremely low quality loss
DeepSeek-Coder-V2-Instruct-Q6_K-00005-of-00007.gguf Q6_K 6 29.3 GB very large, extremely low quality loss
DeepSeek-Coder-V2-Instruct-Q6_K-00006-of-00007.gguf Q6_K 6 29.3 GB very large, extremely low quality loss
DeepSeek-Coder-V2-Instruct-Q6_K-00007-of-00007.gguf Q6_K 6 17.3 GB very large, extremely low quality loss
DeepSeek-Coder-V2-Instruct-Q8_0-00001-of-00009.gguf Q8_0 8 29.7 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-Q8_0-00002-of-00009.gguf Q8_0 8 29.6 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-Q8_0-00003-of-00009.gguf Q8_0 8 29.6 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-Q8_0-00004-of-00009.gguf Q8_0 8 29.6 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-Q8_0-00005-of-00009.gguf Q8_0 8 29.6 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-Q8_0-00006-of-00009.gguf Q8_0 8 29.6 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-Q8_0-00007-of-00009.gguf Q8_0 8 29.6 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-Q8_0-00008-of-00009.gguf Q8_0 8 29.6 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-Q8_0-00009-of-00009.gguf Q8_0 8 14.0 GB very large, extremely low quality loss - not recommended
DeepSeek-Coder-V2-Instruct-f16-00001-of-00017.gguf f16 16 29.5 GB
DeepSeek-Coder-V2-Instruct-f16-00002-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00003-of-00017.gguf f16 16 28.9 GB
DeepSeek-Coder-V2-Instruct-f16-00004-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00005-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00006-of-00017.gguf f16 16 28.9 GB
DeepSeek-Coder-V2-Instruct-f16-00007-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00008-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00009-of-00017.gguf f16 16 28.9 GB
DeepSeek-Coder-V2-Instruct-f16-00010-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00011-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00012-of-00017.gguf f16 16 28.5 GB
DeepSeek-Coder-V2-Instruct-f16-00013-of-00017.gguf f16 16 29.7 GB
DeepSeek-Coder-V2-Instruct-f16-00014-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00015-of-00017.gguf f16 16 28.9 GB
DeepSeek-Coder-V2-Instruct-f16-00016-of-00017.gguf f16 16 29.3 GB
DeepSeek-Coder-V2-Instruct-f16-00017-of-00017.gguf f16 16 5.03 GB

Quatized with llama.cpp b3499

Downloads last month
266
GGUF
Model size
236B params
Architecture
deepseek2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference API
Inference API (serverless) has been turned off for this model.

Model tree for second-state/DeepSeek-Coder-V2-Instruct-GGUF