Models

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.

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.

openthinker

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

r1-1776

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

RuCoverLAB/deepseek-r1-8b-abliterated-q4

richardyoung/deepseek-r1-0528-qwen3-8b-heretic

Uncensored DeepSeek-R1-0528-Qwen3-8B via Heretic: 4/100 refusals (from 89), KL 0.041. Reasoning model, MIT.

s1gnature/deepseek-r1-uncensored

leleziar/deepseek-r1-uncensored-english

erukude/cve-expert

A fine-tuned DeepSeek-R1-70B model for CVE-worthiness review, exploit-path analysis, and JSON-only vulnerability triage.

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

DeepSeek-R1-0528-Qwen3-8B

ttempvnn/DeepSeek-R1-Distill-Qwen-32B-abliterated-Q4-K-M

iapp/openthai-r1-32b

Thai reasoning model that shows its step-by-step thinking — beats DeepSeek R1 70B and Typhoon R1 70B on Thai benchmarks (avg 71.58 vs 63.31/65.42) at half their size. ~24 GB RAM.

lcz2026/DeepSeek-R1-8B

Beelzebub4883/deepseek-r1-1.5b

openthai/openthai-r1-32b

Thai reasoning model that shows its step-by-step thinking — beats DeepSeek R1 70B and Typhoon R1 70B on Thai benchmarks (avg 71.58 vs 63.31/65.42) at half their size. ~24 GB RAM.

danikvanek/deepseek-r1

media-pipe/deepseek-r1

dzgg/deepseek-R1-ablated

dtarkent2/sprocket-gex-deepseek-r1-14b-paper-exact

dirkiedevelopment/deepseek-r1-8b