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

61M Pulls 35 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

1.2M 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

596.3K Pulls 15 Tags Updated 5 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

104.7K Pulls 9 Tags Updated 6 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

66K Pulls 7 Tags Updated 12 months ago

deepseek-v3.1

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode.

tools thinking 671b

34K Pulls 4 Tags Updated 1 week ago

deepseek-v3

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

671b

2.2M Pulls 5 Tags Updated 7 months ago

erwan2/DeepSeek-Janus-Pro-7B

5.4M Pulls 1 Tag Updated 7 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

561.5K Pulls 55 Tags Updated 3 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 7 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.

101K Pulls 1 Tag Updated 7 months ago

Huzderu/deepseek-r1-671b-2.51bit

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

60.4K Pulls 1 Tag 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 7 months ago

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

25.2K Pulls 4 Tags Updated 4 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

23.8K Pulls 26 Tags Updated 7 months ago

nezahatkorkmaz/deepseek-v3

DeepSeek-V3 from Huggingface: Your powerful solution for handling complex requests and advanced coding tasks. Enhance your development workflow with state-of-the-art code assistance and intelligent problem-solving capabilities.

tools

18.8K Pulls 1 Tag Updated 8 months ago

Huzderu/deepseek-r1-671b-2.22bit

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

5,862 Pulls 1 Tag Updated 7 months ago

deepseek-140B/DeepSeekAI140B

5,603 Pulls 1 Tag Updated 7 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.

5,343 Pulls 2 Tags Updated 7 months ago

gguf/DeepSeek-Janus-Pro-7B

Ollama models of DeepSeek Janus Pro 7B

5,220 Pulls 11 Tags Updated 7 months ago