DeepSeek · Ollama

deepseek-v4-pro

DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.

143.6K Pulls 1 Tag Updated 1 month ago

deepseek-v4-flash

DeepSeek-V4-Flash is a preview of the DeepSeek-V4 series, a Mixture-of-Experts model with 284B total parameters and 13B activated, built for efficient reasoning across a 1M-token context window.

tools thinking cloud

134.7K Pulls 1 Tag Updated 2 months ago

deepseek-v3.2

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

tools thinking cloud

2.2M Pulls 1 Tag Updated 6 months ago

deepseek-ocr

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

vision 3b

476.4K Pulls 3 Tags Updated 7 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

701.6K Pulls 8 Tags Updated 7 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

88.5M Pulls 35 Tags Updated 11 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

4.3M Pulls 102 Tags Updated 2 years ago

openthinker

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

7b 32b

1.1M Pulls 15 Tags Updated 1 year 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

406.8K Pulls 9 Tags Updated 1 year 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

278K 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

3.8M Pulls 5 Tags Updated 1 year ago

saadmanhere/dragonglass

Dragonglass is an autonomous, agentic configuration of the `deepseek-v4-pro:cloud` model. It leverages DeepSeek's 1.6T parameter Mixture-of-Experts architecture and 1M-token context window to execute complex, multi-step workflows with high reliability.

cloud

71 Pulls 1 Tag Updated 3 weeks ago

pdurugyan/qwen3.5-9b-deepseek-v4-flash-Q4_K_M-v_2

Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4. + vision. ollama v.0.30.0-rc20 +

vision tools thinking

3,589 Pulls 1 Tag Updated 1 month ago

ZimaBlueAI/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

tools thinking

2,830 Pulls 1 Tag Updated 1 month ago

pdurugyan/qwen3.5-9b-deepseek-v4-flash-Q4_K_M

Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4.

tools thinking

1,710 Pulls 1 Tag Updated 1 month ago

novaforgeai/deepseek-coder

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

2,511 Pulls 1 Tag Updated 5 months ago

brsilvapimentel/DeepSeek-R1-0528-Qwen3-8B

DeepSeek-R1-0528-Qwen3-8B

tools

744 Pulls 1 Tag Updated 1 month ago

iradukundadev/finetuned-deepseek-r1_7b

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

thinking

466 Pulls 1 Tag Updated 5 months ago

DedeProGames/smallcoder

SmallCoder is a compact reasoning-focused coding model, fine-tuned from DeepSeek-R1 1.5B using a code dataset that includes step-by-step reasoning.

1.5b

292 Pulls 1 Tag Updated 4 months ago

rjeffvalle/coder-pro

Based on DeepSeek R1 because OpenCode tries to verify on the registry for tool compatibility

tools

219 Pulls 1 Tag Updated 3 months ago