Directories / Alternatives / DeepSeek-R1

Open Source Alternatives

Open source alternatives to DeepSeek-R1

Open source alternatives to DeepSeek-R1, ranked by GitHub stars and freshness.

22 open-source alternatives in the index, ranked by GitHub stars and freshness.

O OSS Framework medium

open-r1

Community

Fully open reproduction of DeepSeek-R1

★ 26,029 updated 3mo ago

open-source

Best for: Researchers and builders needing transparent, locally-controlled reasoning models

O OSS Framework medium

Kimi-K2

Community

Kimi K2 is the large language model series developed by Moonshot AI team

★ 10,819 updated 5mo ago

open-source

Best for: Developers exploring open-source large language models for custom applications

O OSS Framework medium

Baichuan-7|13B

Community

AGI Large Language Models

open-source

Best for: Developers and researchers needing an open-source, Chinese-capable large language model for fine-tuning and deployment

O OSS Framework medium

DeepSeek-V2.5

Community

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

open-source

Best for: Developers and researchers who need a capable, open-source language model for customization and self-hosting.

O OSS Framework medium

Gemma2-9|27B

Community

Gemma 2, our next generation of open models, is now available globally for researchers and developers.

open-source

Best for: Developers and researchers who need open, efficient models for fine-tuning or production deployment

O OSS Framework medium

GLM-2|6|10|13|70B

Community

Org profile for THUDM on Hugging Face, the AI community building the future.

open-source

Best for: Developers and researchers who need open-source, customizable Chinese-English LLMs for fine-tuning or deployment.

O OSS Framework medium

Grok-1-314B-MoE

Community

Grok-1-314B-MoE — indexed from awesome-llm

open-source

Best for: Researchers and teams with high-end hardware who need an extremely large open-source language model

O OSS Framework medium

Llama 3.2-1|3|11|90B

Community

[Llama 3.1-8 70 405B](https://llama.meta.com/)

open-source

Best for: Developers who need a versatile, open-source LLM for deployment across devices

O OSS Framework medium

MiniCPM-2B

Community

The MiniCPM family of LLMs and VLLMs.

open-source

Best for: Developers needing a free, lightweight model for prototyping or deployment on low-resource devices

O OSS Framework medium

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.

open-source

Best for: Developers and teams who need a high-quality open-source model for fine-tuning and self-hosted deployment

O OSS Framework medium

Moonlight-A3B

Community

Moonshot's Compute-efficient MoE LLM, first Scaling Up of Muon Optimizer

open-source

Best for: Developers exploring efficient MoE language models or the Muon optimizer at scale

O OSS Framework medium

Nemotron-4-340B

Community

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

open-source

Best for: Developers and researchers who need a powerful, open foundation model for instruction following and reasoning

O OSS Framework medium

OpenAI o3-mini

Community

Pushing the frontier of cost-effective reasoning.

open-source

Best for: Developers who need a budget-friendly reasoning model for production use.

O OSS Framework medium

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

open-source

Best for: Developers needing a flexible, open-source LLM family with strong multilingual and coding capabilities

O OSS Framework medium

Qwen-1.8B|7B|14B|72B

Community

Qwen - a Qwen Collection

open-source

Best for: Developers seeking scalable open-source LLMs for diverse deployment environments

O OSS Framework medium

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

open-source

Best for: Developers exploring open-source MoE large language models for integration

O OSS Framework medium

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

open-source

Best for: Developers who need a math-focused reasoning model within a resource-constrained or open-source pipeline

O OSS Framework medium

StableLM-3B

Community

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

open-source

Best for: Developers or hobbyists needing a compact, open-source language model for lightweight applications

O OSS Framework medium

StableLM-v2-12B

Community

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

open-source

Best for: Developers seeking a capable, open-source language model for moderate-scale text generation tasks

O OSS Framework medium

StarCoder-1|3|7B

Community

All models, datasets, and demos related to StarCoder!

open-source

Best for: Developers who want a free, open-source code completion model they can run locally or customize

O OSS Framework medium

Yi-34B

Community

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

open-source

Best for: Developers and researchers who need a capable open-source LLM for self-hosted or customized applications.

P Apps Productivity low

Grok

Various

An LLM by xAI with [open source](https://github.com/xai-org/grok-1) and open weights. #opensource

freemium

Best for: Developers and organizations seeking a transparent, customizable, and self-hostable LLM for research or production use