DeepSeek-R1
by Community
First-generation reasoning models from DeepSeek.
OSS
DeepSeek-R1
Added 1 June 2026
Overview
DeepSeek-R1 is an open-source reasoning model designed to perform multi-step logical inference and problem-solving tasks. It uses chain-of-thought reasoning to work through complex problems step-by-step before generating answers. Available as a framework for local deployment and integration.
Best for
Best for
Developers building open-source applications needing interpretable multi-step reasoning without vendor lock-in
Use cases
- Mathematical problem solving and verification
- Code generation with reasoning about correctness
- Logical inference and constraint satisfaction tasks
Notes
DeepSeek-R1 is an open-source reasoning model designed to perform multi-step logical inference and problem-solving tasks. It uses chain-of-thought reasoning to work through complex problems step-by-step before generating answers. Available as a framework for local deployment and integration.
92,010 stars on GitHub. Last updated 2025-06-27. Licensed MIT.
Use cases
- Mathematical problem solving and verification
- Code generation with reasoning about correctness
- Logical inference and constraint satisfaction tasks
Pros
- Open-source and freely available for local deployment
- Transparent reasoning process shows intermediate steps
- Strong community adoption with 92k GitHub stars
Cons
- First-generation model with unproven performance against commercial reasoning systems
- Requires significant compute resources for inference
- Limited documentation on specific reasoning capabilities and failure modes
Indexed from awesome-llm and enriched against its public facts.
Pros
- Open-source and freely available for local deployment
- Transparent reasoning process shows intermediate steps
- Strong community adoption with 92k GitHub stars
Cons
- First-generation model with unproven performance against commercial reasoning systems
- Requires significant compute resources for inference
- Limited documentation on specific reasoning capabilities and failure modes
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
ollama
Community
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
vLLM
Community
A high-throughput and memory-efficient inference and serving engine for LLMs
SGLang
Community
SGLang is a high-performance serving framework for large language models and multimodal models.
open-r1
Community
Fully open reproduction of DeepSeek-R1
TinyZero
Community
Minimal reproduction of DeepSeek R1-Zero
veRL
Community
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
unslothai
Community
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
arikusi/deepseek-mcp-server
Various
MCP Server for DeepSeek API - enables MCP clients to use DeepSeek Chat and Reasoner models
OthmaneBlial/term_mcp_deepseek
Various
A MCP‑like server using the DeepSeek API for Terminal
PsChina/deepseek-as-subagent
Various
Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — DeepSeek gets its own 7-tool agent loop in a sandboxed workspace, not just a single LLM call.
Google "We Have No Moat, And Neither Does OpenAI"
Community
Leaked Internal Google Document Claims Open Source AI Will Outcompete Google and OpenAI
Reasoning using Language Models
Community
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓
Baichuan-7|13B
Community
AGI Large Language Models
DeepSeek-V2.5
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Gemma2-9|27B
Community
Gemma 2, our next generation of open models, is now available globally for researchers and developers.
GLM-2|6|10|13|70B
Community
Org profile for THUDM on Hugging Face, the AI community building the future.
Grok-1-314B-MoE
Community
Grok-1-314B-MoE — indexed from awesome-llm
Kimi-K2
Community
Kimi K2 is the large language model series developed by Moonshot AI team
Llama 3.2-1|3|11|90B
Community
[Llama 3.1-8 70 405B](https://llama.meta.com/)
MiniCPM-2B
Community
The MiniCPM family of LLMs and VLLMs.
Mixtral-8x7B
Community
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
Moonlight-A3B
Community
Moonshot's Compute-efficient MoE LLM, first Scaling Up of Muon Optimizer
Nemotron-4-340B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
open-r1
Community
Fully open reproduction of DeepSeek-R1
OpenAI o3-mini
Community
Pushing the frontier of cost-effective reasoning.
Qwen2-0.5B|1.5B|7B|57B-A14B-MoE|72B
Community
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you: Pret
Qwen-1.8B|7B|14B|72B
Community
Qwen - a Qwen Collection
Qwen2.5-Max
Community
QWEN CHAT API DEMO DISCORD It is widely recognized that continuously scaling both data size and model size can lead to significant improvements in model intelligence. However, th
Qwen2-Math-1.5B|7B|72B
Community
GITHUB HUGGING FACE MODELSCOPE DISCORD 🚨 This model mainly supports English. We will release bilingual (English and Chinese) math models soon. Introduction Over the past year, w
StableLM-3B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
StableLM-v2-12B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
StarCoder-1|3|7B
Community
All models, datasets, and demos related to StarCoder!
Yi-34B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Grok
Various
An LLM by xAI with [open source](https://github.com/xai-org/grok-1) and open weights. #opensource
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.