The best LlamaFactory alternatives

vllm

vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Choose vllm if…

• you specifically need amd or blackwell

Shares deepseek, gpt, llama, llm with LlamaFactory.

AstrBot

AstrBotDevs/AstrBot

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

Choose AstrBot if…

• GNU Affero General Public License v3.0 suits your use better than Apache License 2.0
• you specifically need astrbot or chatbot

Shares agent, ai, gpt, llama with LlamaFactory.

inference

xorbitsai/inference

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

Choose inference if…

• you prefer a smaller, narrower project to a large one
• you specifically need artificial-intelligence or deployment

Shares gemma, llm, qwen, transformers with LlamaFactory.

unsloth

unslothai/unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

Choose unsloth if…

• you specifically need chatgpt or gemma

Shares agent, ai, deepseek, fine-tuning with LlamaFactory.

transformers

huggingface/transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Choose transformers if…

• you want the more widely starred option (168.5k)
• you specifically need audio or deep-learning

Shares deepseek, gemma, llm, nlp with LlamaFactory.

sglang

sgl-project/sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

Choose sglang if…

• you specifically need attention or blackwell

Shares deepseek, llama, llm, moe with LlamaFactory.

AdalFlow

SylphAI-Inc/AdalFlow

AdalFlow: The library to build & auto-optimize LLM applications.

Choose AdalFlow if…

• MIT License suits your use better than Apache License 2.0
• you prefer a smaller, narrower project to a large one
• you specifically need auto-prompting or bm25

Shares agent, ai, llm, nlp with LlamaFactory.

Langchain-Chatchat

chatchat-space/Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

Choose Langchain-Chatchat if…

• you specifically need chatbot or chatchat

Shares gpt, llama, llm, qwen with LlamaFactory.

khoj

khoj-ai/khoj

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Choose khoj if…

• GNU Affero General Public License v3.0 suits your use better than Apache License 2.0
• you specifically need assistant or chat

Shares agent, ai, llama3, llm with LlamaFactory.

Soup

MakazhanAlpamys/Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

Choose Soup if…

• you prefer a smaller, narrower project to a large one
• you specifically need cli or consumer-gpu

Shares fine-tuning, llm, lora, peft with LlamaFactory.

h2o-llmstudio

h2oai/h2o-llmstudio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Choose h2o-llmstudio if…

• you prefer a smaller, narrower project to a large one
• you specifically need chatbot or chatgpt

Shares ai, fine-tuning, gpt, llama with LlamaFactory.

airllm

lyogavin/airllm

AirLLM 70B inference with single 4GB GPU

Choose airllm if…

• you would rather work in Jupyter Notebook than Python
• you specifically need chinese-llm or chinese-nlp

Shares llama, llm, lora, qlora with LlamaFactory.