deepseek · Ollama Search

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

65.8M Pulls 35 Tags Updated 3 months ago

deepseek-v3.1

DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

tools thinking cloud 671b

96.8K Pulls 8 Tags Updated 2 weeks 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

555K Pulls 6 Tags Updated 7 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

24.7K Pulls 26 Tags Updated 8 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

16.2K Pulls 510 Tags Updated 8 months ago

michaelneale/deepseek-r1-goose

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

tools 70b

5,018 Pulls 2 Tags Updated 8 months ago

nuibang/Cline_FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview

Adapted for Cline tool / Roo Code use in VS Code fused model , hybrid of DeepSeekR1 and Qwen2.5 coder, from FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview.

tools

4,213 Pulls 2 Tags Updated 8 months ago