metadata

base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
license: apache-2.0
license_link: >-
  https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/LICENSE
model_creator: deepseek-ai
model_name: DeepSeek-R1-Distill-Qwen-7B
quantized_by: Second State Inc.
library_name: transformers

DeepSeek-R1-Distill-Qwen-7B-GGUF

Original Model

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Run with LlamaEdge

LlamaEdge version: v0.16.8

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: 128000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf \
  llama-api-server.wasm \
  --model-name DeepSeek-R1-Distill-Qwen-7B \
  --prompt-template chatml \
  --ctx-size 128000

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template chatml \
  --ctx-size 128000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf	Q2_K	2	3.02 GB	smallest, significant quality loss - not recommended for most purposes
DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf	Q3_K_L	3	4.09 GB	small, substantial quality loss
DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf	Q3_K_M	3	3.81 GB	very small, high quality loss
DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf	Q3_K_S	3	3.49 GB	very small, high quality loss
DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf	Q4_0	4	4.43 GB	legacy; small, very high quality loss - prefer using Q3_K_M
DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf	Q4_K_M	4	4.68 GB	medium, balanced quality - recommended
DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf	Q4_K_S	4	4.46 GB	small, greater quality loss
DeepSeek-R1-Distill-Qwen-7B-Q5_0.gguf	Q5_0	5	5.32 GB	legacy; medium, balanced quality - prefer using Q4_K_M
DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf	Q5_K_M	5	5.44 GB	large, very low quality loss - recommended
DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf	Q5_K_S	5	5.32 GB	large, low quality loss - recommended
DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf	Q6_K	6	6.25 GB	very large, extremely low quality loss
DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf	Q8_0	8	8.21 GB	very large, extremely low quality loss - not recommended
DeepSeek-R1-Distill-Qwen-7B-f16.gguf	f16	16	15.2 GB

Quantized with llama.cpp b4519