DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
A fine-tuned DeepSeek-R1-70B model for CVE-worthiness review, exploit-path analysis, and JSON-only vulnerability triage.
Uncensored DeepSeek-R1-0528-Qwen3-8B via Heretic: 4/100 refusals (from 89), KL 0.041. Reasoning model, MIT.
Omnigenesis Lyapunov stability specialist based on DeepSeek R1 1.5B
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.
Omnigenesis five-section synthesis orchestrator based on DeepSeek R1 7B
DeepSeek-R1-0528-Qwen3-8B
Huggingface link - https://huggingface.co/iradukunda-dev/law-finetuned-DeepSeek-R1-Distill-Qwen-7B
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.
Based on DeepSeek R1 because OpenCode tries to verify on the registry for tool compatibility
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
SmallCoder is a compact reasoning-focused math model, fine-tuned from DeepSeek-R1 1.5B using a math dataset that includes step-by-step reasoning.
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.
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.