deepseek-r1

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

tools thinking 1.5b 7b 8b 14b 32b 70b 671b

74.5M Pulls 35 Tags Updated 5 months ago

ishumilin/deepseek-r1-coder-tools

This is a modified model that adds support for autonomous coding agents like Cline

tools 1.5b 7b 8b 14b 32b 70b

556.1K Pulls 6 Tags Updated 9 months ago

MFDoom/deepseek-r1-tool-calling

DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen. With Tool Calling support.

tools 1.5b 7b 8b 14b 32b 70b 671b

26.4K Pulls 26 Tags Updated 10 months ago

tom_himanen/deepseek-r1-roo-cline-tools

This version of Deepseek R1 is optimized for tool usage with Cline and Roo Code.

tools 1.5b 7b 8b 14b 32b 70b

17.1K Pulls 510 Tags Updated 10 months ago

michaelneale/deepseek-r1-goose

Tool calling for deepseek-r1, tweaked for the goose agent

tools 70b

5,227 Pulls 2 Tags Updated 10 months ago

rns96/deepseek-R1-ablated

Many quantized GGUF versions of deepseek R1 abliterated (uncensored) with tools support

tools

4,613 Pulls 8 Tags Updated 10 months ago

nvjob/DeepSeek-R1-32B-Cline

Adapted to work with Cline (Claude Dev) Visual Studio Code

tools

3,012 Pulls 1 Tag Updated 10 months ago

ishumilin/deepseek-r1-coder-tools-tuned

tools 1.5b 7b 8b 14b 32b 70b

2,012 Pulls 6 Tags Updated 9 months ago

okamototk/deepseek-r1

DeepSeek R1 0528 Qwen3 8B with tool calling/MCP support

tools thinking 8b

1,907 Pulls 1 Tag Updated 5 months ago

heatxsink/cline-tools.deepseek-r1

Deepseek R1 optimized for tool usage with Cline.

tools 8b 14b 32b

1,661 Pulls 3 Tags Updated 9 months ago

mychen76/deepseek_r1_cline_roocode

Quantized version of DeepSeek-R1-32B optimized for tool usage with Cline / Roo Code and complex problem solving.

tools 32b

1,490 Pulls 1 Tag Updated 7 months ago

huihui_ai/tinyr1-abliterated

Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math.

tools 32b

1,321 Pulls 6 Tags Updated 9 months ago

lucasmg/deepseek-r1-8b-0528-qwen3-q4_K_M-tool-true

DeepSeek R1 0528 Qwen3 8B Q4 with tool calling

tools thinking

1,125 Pulls 1 Tag Updated 6 months ago

kwangsuklee/DeepSeek-R1-Distill-Qwen-7B-Multilingual-Q5_K_M

Optimized for 38 languages

tools

571 Pulls 1 Tag Updated 10 months ago

sammcj/deepseek-r1-distilled-llama-70b

tools

235 Pulls 1 Tag Updated 10 months ago

call518/deepseek-r1-tool-calling

FROM "MFDoom/deepseek-r1-tool-calling"

tools 1.5b 7b

189 Pulls 2 Tags Updated 10 months ago

futuretea/deepseek-r1-cline

tools 14b 32b

144 Pulls 2 Tags Updated 9 months ago

bjoernb/deepseek-r1-8b

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

tools thinking

139 Pulls 1 Tag Updated 4 months ago

lwk/r1

ollama run deepseek-r1

tools

88 Pulls 1 Tag Updated 10 months ago

rjmalagon/deepseek-r1-distill-qwen

tools

84 Pulls 2 Tags Updated 11 months ago