Alternatives and similar repositories for DeepSeek-R1

Users that are interested in DeepSeek-R1 are comparing it to the libraries listed below

• deepseek-ai / DeepSeek-V3
  ☆100,291Updated 2 months ago
• deepseek-ai / Janus
  Janus-Series: Unified Multimodal Understanding and Generation Models
  ☆17,608Updated 9 months ago
• deepseek-ai / DeepSeek-Coder
  DeepSeek Coder: Let the Code Write Itself
  ☆22,360Updated last week
• QwenLM / Qwen3
  Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
  ☆25,425Updated last month
• huggingface / open-r1
  Fully open reproduction of DeepSeek-R1
  ☆25,648Updated 2 months ago
• deepseek-ai / awesome-deepseek-integration
  Integrate the DeepSeek API into popular softwares
  ☆34,428Updated last month
• unslothai / unsloth
  Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
  ☆48,289Updated this week
• deepseek-ai / DeepSeek-VL2
  DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
  ☆5,118Updated 8 months ago
• deepseek-ai / FlashMLA
  FlashMLA: Efficient Multi-head Latent Attention Kernels
  ☆11,866Updated last month
• QwenLM / Qwen3-VL
  Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆16,371Updated last week
• deepseek-ai / DeepSeek-LLM
  DeepSeek LLM: Let there be answers
  ☆6,613Updated last year
• QwenLM / Qwen
  The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
  ☆19,725Updated last month
• hiyouga / LLaMA-Factory
  Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
  ☆62,602Updated last week
• meta-llama / llama3
  The official Meta Llama 3 GitHub site
  ☆29,094Updated 9 months ago
• deepseek-ai / DeepSeek-Coder-V2
  DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
  ☆6,217Updated last week
• vllm-project / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆63,144Updated this week
• QwenLM / Qwen3-Coder
  Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.
  ☆14,335Updated 3 months ago
• deepseek-ai / DeepEP
  DeepEP: an efficient expert-parallel communication library
  ☆8,723Updated this week
• Jiayi-Pan / TinyZero
  Minimal reproduction of DeepSeek R1-Zero
  ☆12,399Updated 6 months ago
• deepseek-ai / open-infra-index
  Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
  ☆7,926Updated 6 months ago
• open-webui / open-webui
  User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
  ☆115,188Updated this week
• microsoft / OmniParser
  A simple screen parsing tool towards pure vision based GUI agent
  ☆23,832Updated 2 months ago
• ollama / ollama
  Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
  ☆156,090Updated this week
• deepseek-ai / DeepSeek-V2
  DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
  ☆4,963Updated last year
• browser-use / browser-use
  🌐 Make websites accessible for AI agents. Automate tasks online with ease.
  ☆72,584Updated this week
• kvcache-ai / ktransformers
  A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
  ☆15,663Updated last week
• CherryHQ / cherry-studio
  🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
  ☆35,416Updated this week
• rasbt / LLMs-from-scratch
  Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
  ☆78,762Updated last week
• microsoft / markitdown
  Python tool for converting files and office documents to Markdown.
  ☆83,106Updated 3 weeks ago
• jingyaogong / minimind
  🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
  ☆33,580Updated last week