DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
92.7M Pulls 35 Tags Updated 1 year ago
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.
1.3M Pulls 5 Tags Updated 1 year ago
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
1.2M Pulls 15 Tags Updated 1 year ago
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
421.6K Pulls 9 Tags Updated 1 year ago
DeepSeek-V4-Flash is the official release of DeepSeek-V4-Flash, built for efficient reasoning across a 1M-token context window, outperforming DeepSeek-V4-Pro (Preview).
448.7K Pulls 2 Tags Updated 1 month ago
7 Pulls 2 Tags Updated 4 days ago
A fine-tuned DeepSeek-R1-70B model for CVE-worthiness review, exploit-path analysis, and JSON-only vulnerability triage.
3,453 Pulls 1 Tag Updated 4 weeks ago
134 Pulls 1 Tag Updated 1 week ago
92 Pulls 1 Tag Updated 2 weeks ago
I have just enabled both calling and thinking to existing deepseek-r1 models.
2,832 Pulls 6 Tags Updated 4 months ago
2,749 Pulls 2 Tags Updated 5 months ago
ollama run f0rc3ps/deepseek-r1-32b-uncensored:nu11secur1ty
1,689 Pulls 1 Tag Updated 5 months ago
DeepSeek-R1-0528-Qwen3-8B
1,202 Pulls 1 Tag Updated 4 months ago
118 Pulls 1 Tag Updated 1 month ago
221 Pulls 1 Tag Updated 4 months ago
Thai reasoning model that shows its step-by-step thinking — beats DeepSeek R1 70B and Typhoon R1 70B on Thai benchmarks (avg 71.58 vs 63.31/65.42) at half their size. ~24 GB RAM.
97 Pulls 2 Tags Updated 1 month ago
103 Pulls 1 Tag Updated 2 months ago
131 Pulls 1 Tag Updated 5 months ago
97 Pulls 1 Tag Updated 3 months ago
71 Pulls 1 Tag Updated 2 months ago