20+ models
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
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.
`DeepSeekR1-QwQ-SkyT1-32B-Fusion` is a mixed model that combines the strengths of three powerful Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated, huihui-ai/QwQ-32B-Preview-abliterated and huihui-ai/Sky-T1-32B-Preview-abliterated
The quantized versions of the FuseO1 + DeepSeek R1 + QwQ + Sky T1 Fusion Model
Uncensored DeepSeek-R1-0528-Qwen3-8B via Heretic: 4/100 refusals (from 89), KL 0.041. Reasoning model, MIT.
A fine-tuned DeepSeek-R1-70B model for CVE-worthiness review, exploit-path analysis, and JSON-only vulnerability triage.
DeepSeek-R1-0528-Qwen3-8B