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

74.2M Pulls 35 Tags Updated 5 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

198.9K Pulls 8 Tags Updated 2 months ago

deepseek-coder

DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.

1.3b 6.7b 33b

2.2M Pulls 102 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

627K Pulls 15 Tags Updated 8 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

152.2K Pulls 9 Tags Updated 9 months ago

deepseek-v2.5

An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.

236b

89K Pulls 7 Tags Updated 1 year ago

deepseek-ocr

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

vision 3b

57.6K Pulls 3 Tags Updated 3 weeks ago

deepseek-v3.2

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

cloud

2,881 Pulls 1 Tag Updated 5 days ago

deepseek-v3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

671b

2.9M Pulls 5 Tags Updated 11 months ago

erwan2/DeepSeek-Janus-Pro-7B

5.4M Pulls 1 Tag Updated 10 months ago

huihui_ai/deepseek-r1-abliterated

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.

thinking 1.5b 7b 8b 14b 32b 70b

606.5K Pulls 55 Tags Updated 6 months ago

secfa/DeepSeek-R1-UD-IQ1_S

Unsloth's DeepSeek-R1 , I just merged the thing and uploaded it here. This is the full 671b model. MoE Bits:1.58bit Type:UD-IQ1_S Disk Size:131GB Accuracy:Fair Details:MoE all 1.56bit. down_proj in MoE mixture of 2.06/1.56bit

170.9K Pulls 2 Tags Updated 10 months ago

hengwen/DeepSeek-R1-Distill-Qwen-32B

DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. Please use our setting to run these models.

118.7K Pulls 2 Tags Updated 10 months ago

SIGJNF/deepseek-r1-671b-1.58bit

Unsloth's DeepSeek-R1 1.58-bit, I just merged the thing and uploaded it here. This is the full 671b model, albeit dynamically quantized to 1.58bits.

101.4K Pulls 1 Tag Updated 10 months ago

Huzderu/deepseek-r1-671b-2.51bit

Merged GGUF Unsloth's DeepSeek-R1 671B 2.51bit dynamic quant

60.5K Pulls 1 Tag Updated 10 months ago

thirdeyeai/DeepSeek-R1-Distill-Qwen-7B-uncensored

28.9K Pulls 4 Tags Updated 7 months ago

Huzderu/deepseek-r1-671b-1.73bit

Merged GGUF Unsloth's DeepSeek-R1 671B 1.73bit dynamic quant

26.7K Pulls 1 Tag Updated 10 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

26.2K Pulls 26 Tags Updated 10 months ago

Huzderu/deepseek-r1-671b-2.22bit

Merged GGUF Unsloth's DeepSeek-R1 671B 2.22bit dynamic quant

5,867 Pulls 1 Tag Updated 10 months ago

deepseek-140B/DeepSeekAI140B

5,659 Pulls 1 Tag Updated 10 months ago