Models

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.

aleshribar3/deepseek-r1-tool-calling

I have just enabled both calling and thinking to existing deepseek-r1 models.

brsilvapimentel/DeepSeek-R1-0528-Qwen3-8B

DeepSeek-R1-0528-Qwen3-8B

aleshribar3/deepseek-r1

I have just enabled both calling and thinking to existing deepseek-r1 models.

dzgg/deepseek-R1-ablated

milanjeremic2/deepseek-r1-32b-uncensored

ollama run f0rc3ps/deepseek-r1-32b-uncensored:nu11secur1ty

rjeffvalle/coder-pro

Based on DeepSeek R1 because OpenCode tries to verify on the registry for tool compatibility

ishumilin/deepseek-r1-coder-tools

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

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.

tom_himanen/deepseek-r1-roo-cline-tools

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

rns96/deepseek-R1-ablated

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

michaelneale/deepseek-r1-goose

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

okamototk/deepseek-r1

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

nvjob/DeepSeek-R1-32B-Cline

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

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

DeepSeek R1 0528 Qwen3 8B Q4 with tool calling

ishumilin/deepseek-r1-coder-tools-tuned

heatxsink/cline-tools.deepseek-r1

Deepseek R1 optimized for tool usage with Cline.

mychen76/deepseek_r1_cline_roocode

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

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.

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