DeepSeek · Ollama

deepseek-ocr

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

vision 3b

141.5K Pulls 3 Tags Updated 2 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

308.4K Pulls 8 Tags Updated 4 months ago

deepseek-v3.2

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

cloud

22.8K Pulls 1 Tag Updated 1 month ago

openthinker

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

7b 32b

742.5K Pulls 15 Tags Updated 10 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

217K Pulls 9 Tags Updated 11 months ago

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

77.4M Pulls 35 Tags Updated 7 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

2.9M Pulls 102 Tags Updated 2 years 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

132.8K Pulls 7 Tags Updated 1 year ago

deepseek-v3

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

671b

3.3M Pulls 5 Tags Updated 1 year ago

novaforgeai/deepseek-coder

NovaForge AI – DeepSeek Coder 6.7B Pro is a professional-grade coding AI built for production-level development.

594 Pulls 1 Tag Updated 4 weeks ago

iradukundadev/finetuned-deepseek-r1_7b

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

thinking

73 Pulls 1 Tag Updated 4 weeks ago

second_constantine/deepseek-coder-v2

This is a brand new Mixture of Export (MoE) model from DeepSeek, specializing in coding instructions. (quantized IQ4_XS)

tools 16b

1,337 Pulls 3 Tags Updated 2 weeks ago

RobiLabs/lexa-rho

Lexa-Rho is part of Lexa Family with performance approaching that of leading models, such as GPT-5 Thinking, Gemini 2.5 Pro and DeepSeek-R1.

8b 70b

305 Pulls 2 Tags Updated 5 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

171K Pulls 2 Tags Updated 12 months ago

kongxiangyiren/Neko-Chat

基于 DeepSeek-R1-Distill-Qwen-1.5B 微调的中文轻量对话模型，自带猫娘口癖与亲昵风格。

124 Pulls 1 Tag Updated 3 months ago

huihui_ai/deepseek-v3.1

This is not the ablation version. DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode.

tools thinking 671b

106 Pulls 3 Tags Updated 5 months ago

gguf/DeepSeek-Janus-Pro-7B

Ollama models of DeepSeek Janus Pro 7B

5,550 Pulls 11 Tags Updated 12 months ago

erwan2/DeepSeek-Janus-Pro-7B-Vision-Encoder

Vision Encoder for Janus Pro 7B. This model is under testing

vision

4,750 Pulls 1 Tag Updated 12 months ago

rockn/DeepSeek-R1-0528-Qwen3-8B-IQ4_NL

DeepSeek-R1-0528-Qwen3-8B-IQ4_NL

3,169 Pulls 1 Tag Updated 8 months ago

secfa/DeepSeek-R1-UD-IQ1_M

Unsloth's DeepSeek-R1 , I just merged the thing and uploaded it here. This is the full 671b model. MoE Bits:1.73bit Type:UD-IQ1_M Disk Size:158GB Accuracy:Good Details:MoE all 1.56bit. down_proj in MoE left at 2.06bit

4,323 Pulls 2 Tags Updated 12 months ago