deepseek R · Ollama

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

81.8M Pulls 35 Tags Updated 9 months ago

deepseek-v3.2

DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.

tools thinking cloud

68.3K Pulls 1 Tag Updated 3 months ago

deepseek-ocr

DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

vision 3b

379.8K Pulls 3 Tags Updated 4 months ago

deepscaler

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.

1.5b

1.2M Pulls 5 Tags Updated 1 year ago

openthinker

A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.

7b 32b

1M Pulls 15 Tags Updated 12 months ago

r1-1776

A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

70b 671b

360K Pulls 9 Tags Updated 1 year ago

1489180953/lanhu_deepseekR1_32b

1 Pull 1 Tag Updated 4 months ago

iradukundadev/finetuned-deepseek-r1_7b

Huggingface link - https://huggingface.co/iradukunda-dev/law-finetuned-DeepSeek-R1-Distill-Qwen-7B

thinking

273 Pulls 1 Tag Updated 2 months ago

okamototk/deepseek-r1

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

tools thinking 8b

2,670 Pulls 1 Tag Updated 8 months ago

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

DeepSeek R1 0528 Qwen3 8B Q4 with tool calling

tools thinking

1,757 Pulls 1 Tag Updated 10 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

1,675 Pulls 1 Tag Updated 11 months ago

lsm03624/deepseek-r1

DeepSeek-R1-0528 仍然使用 2024 年 12 月所发布的 DeepSeek V3 Base 模型作为基座，但在后训练过程中投入了更多算力，显著提升了模型的思维深度与推理能力。这个8B精馏版本编程能力都爆表！

thinking

982 Pulls 1 Tag Updated 10 months ago

mikepfunk28/deepseekq3_agent

16k Context Window meaning you need less RAM to run this. It's full context windows is loaded in the deepseekq3_coder. It allocates the RAM needed for the context when loading the model.

tools thinking

483 Pulls 1 Tag Updated 8 months ago