llamafactory vs minimind
Two of the top projects in Training and fine-tuning, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
llamafactory
Fine-tuning toolkit for 100+ LLMs with a CLI and Gradio web UI
minimind
Train a 64M-parameter LLM from scratch in plain PyTorch
Verdict
llamafactory ranks higher, 74 to 52. Of the 4 score parts we measure for both, llamafactory leads on 3, minimind on 1.
- Adoptionllamafactory leads by 53 points, 91 to 38: a wide gap.
- Freshnessllamafactory leads by 15 points, 100 to 85: a wide gap.
- Maintenanceminimind leads by 13 points, 51 to 38.
- Agent-readyllamafactory leads by 55 points, 55 to 0: a wide gap.
Pick llamafactory if you are
Engineers fine-tuning open LLMs on their own GPUs, with or without code
- Broad method coverage: SFT, PPO, DPO, KTO, ORPO, LoRA, QLoRA via AQLM/AWQ/GPTQ/HQQ/EETQ
- Supports GaLore, BAdam, APOLLO, Muon, DoRA, PiSSA, plus Unsloth and Liger Kernel speedups
Pick minimind if you are
Engineers learning LLM internals by pretraining and fine-tuning small models
- Core algorithms (LoRA, DPO, PPO/GRPO) written in plain PyTorch, not wrapped from trl or peft
- Open datasets for each stage, with mini variants (1.2GB pretrain, 1.6GB SFT) for quick runs
| What we compare | llamafactory | minimind |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 91, widely used | 38, known |
| Freshness | 100, active | 85, active |
| Maintenance | 38, patchy | 51, fair |
| Easy to run | Not scored for this kind | Not scored for this kind |
| Agent-ready | 55, partly | 0, none |
| Facts from GitHub and the README | ||
| Stars | 75.4k | 63.7k |
| License | Apache-2.0 (permissive) | Apache-2.0 (permissive) |
| Last commit | Oct 2026 | Sep 2026 |
| Last release | May 2026 | Oct 2025 |
| Language | Python | Python |
| Docker | Yes | No |
| GPU | Required | Optional |
| arm64 or Apple Silicon | Mentioned | Not stated |
llamafactory
LlamaFactory fine-tunes language and multimodal models through YAML-configured CLI runs or the LLaMA Board Gradio UI. It covers pre-training, SFT, reward modeling, PPO, DPO, KTO and ORPO, with full-tuning, freeze-tuning, LoRA and 2 to 8-bit QLoRA. Trained models can be served through an OpenAI-style API using vLLM or SGLang workers.
Who it is for: Engineers fine-tuning open LLMs on their own GPUs, with or without code
Strengths
- Broad method coverage: SFT, PPO, DPO, KTO, ORPO, LoRA, QLoRA via AQLM/AWQ/GPTQ/HQQ/EETQ
- Supports GaLore, BAdam, APOLLO, Muon, DoRA, PiSSA, plus Unsloth and Liger Kernel speedups
- Covers multimodal and audio models such as Qwen3-VL, LLaVA and Qwen2-Audio
- Runs on NVIDIA, AMD ROCm and Ascend NPU, with hosted Colab and PAI-DSW notebooks
Weaknesses
- Official documentation is marked WIP in the README
- No VRAM or RAM figures in the visible README; hardware requirements unknown here
- Web UI is for training and chat, not a production serving layer
- Many optional backends (vLLM, SGLang, Unsloth, KTransformers) add install complexity
- GPU required
- Docker + Compose
- Needs PyTorch, Hugging Face Transformers, Gradio, vLLM (optional), SGLang (optional)
- Models: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen3
minimind
MiniMind is a from-scratch implementation of a small Qwen3-style decoder-only LLM (64M dense, 198M-A64M MoE) with each training stage written in native PyTorch: pretrain, SFT, LoRA, DPO, PPO/GRPO/CISPO, agentic RL and distillation. It ships datasets, a 6,400-token tokenizer, an OpenAI-compatible server and a Streamlit chat UI. The README states one SFT epoch takes about 2 hours on a single 3090.
Who it is for: Engineers learning LLM internals by pretraining and fine-tuning small models
Strengths
- Core algorithms (LoRA, DPO, PPO/GRPO) written in plain PyTorch, not wrapped from trl or peft
- Open datasets for each stage, with mini variants (1.2GB pretrain, 1.6GB SFT) for quick runs
- Weights convert to transformers, llama.cpp, vllm and ollama; ollama and vllm usage is documented
- Checkpoint resume, DDP and DeepSpeed multi-GPU, wandb or swanlab logging
Weaknesses
- Models are tiny (64M), so output quality is far below mainstream LLMs
- README is primarily in Chinese; the English version is a separate file
- Training data is largely synthetic and distilled, with mixed source licenses
- Native MoE training is about 50% slower than dense, per the README
- GPU optional
- Needs PyTorch, transformers, streamlit (optional WebUI), swanlab or wandb (optional)
- Models: minimind-3 (64M), minimind-3-moe (198M-A64M), minimind2 series, Transformers format, llama.cpp
More in Training and fine-tuning
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.