#4141st of 41 in Training and fine-tuning
torchtune
PyTorch library of LLM fine-tuning recipes driven by YAML configs
- Stars
- 5.8k
- License
- BSD-3-Clause
- Last commit
- Apr 2026
- Last release
- Apr 2025
- Language
- Python
5,664 on 3 Apr 20265,820 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
torchtune provides PyTorch-native recipes for SFT (full, LoRA/QLoRA), knowledge distillation, DPO, PPO, GRPO and quantization-aware training, run through a `tune` CLI and YAML configs. It includes model implementations for Llama, Gemma, Mistral, Phi and Qwen families. The README states development wound down in 2025 and the library is no longer actively maintained.
Who it is for: ML engineers fine-tuning open LLMs in PyTorch on their own GPUs
Strengths
- Covers SFT, KD, DPO, PPO, GRPO and QAT recipes; multi-GPU and multi-node support varies
- README gives measured memory figures, e.g. Llama 3.1 8B QLoRA at 7.4 GiB peak on one 4090
- YAML configs with CLI overrides, plus `tune cp` to copy and edit configs locally
- Runs on NVIDIA, Intel XPU, AMD ROCm, Apple MPS and Ascend NPU devices
Weaknesses
- No longer actively maintained; development wound down in 2025
- Last release was 2025-04-07; newest models listed are Qwen3 and Llama 4
- Tested only against latest stable PyTorch (2.6.0 in README) and nightlies
- Many recipe gaps, e.g. no full-weight KD and no LoRA for PPO or GRPO
What it needs
- GPU required
- Needs PyTorch, torchvision, torchao, Hugging Face Hub
- Models: Llama 3.1/3.2/3.3/4, Llama 3.2 Vision, Mistral 7B, Gemma2, Phi3
Quick answers
Is torchtune open source?
Yes. Its code is on GitHub under the BSD-3-Clause license.
Does torchtune need a GPU?
Yes, it needs a GPU.
Also in Training and fine-tuning
See all 41| Rank | Project | Score |
|---|---|---|
| 1 | unslothDesktop and web app to run and fine-tune local models | 88 out of 100 |
| 2 | peftPython library for LoRA and other parameter-efficient fine-tuning of Transformers models | 86 out of 100 |
| 3 | deepspeedPyTorch library for distributed training of very large models with ZeRO | 85 out of 100 |
| #4 | verlReinforcement learning training library for LLM post-training with PPO and GRPO | 84 out of 100 |
| #5 | trlPost-training library with SFT, DPO, GRPO and KTO trainers | 83 out of 100 |