Unsloth Zoo

Unsloth is an open-source local desktop and web tool for running, training, fine-tuning, and deploying language, diffusion, embedding, audio, and vision models. It supports Windows, macOS, Linux, WSL, multi-GPU setups, NVIDIA, AMD, and Intel GPUs, CPUs, and the Vulkan backend. The project is distributed as Unsloth Desktop, Unsloth Studio, and Unsloth Core. It can run local models, provide an OpenAI-compatible API, connect models to agents and MCP tools, perform search and RAG, and offer remote or LAN access. Its training functions cover reinforcement learning, LoRA, QLoRA, full fine-tuning, pretraining, GRPO, DPO, and FP8, with export formats including GGUF, NVFP4, and FP8. The repository claims that its fine-tuning workflows use two times less training time and 70% less VRAM.

Soup is an open-source Python CLI for fine-tuning and post-training large language models from a YAML configuration and a single training command. It supports supervised fine-tuning, LoRA, QLoRA, preference optimization, quantization, automatic batch-size and GPU detection, and local training without a cloud service. Its optional layer-streaming mode keeps the frozen base model out of VRAM and feeds it to the GPU one decoder layer at a time, reducing memory use for low-VRAM systems. The project describes training an 8B model on a 4 GB laptop GPU with this mode; layer streaming is marked beta.

Soup CLI is a command-line toolkit for training, fine-tuning, evaluating and managing large language models (notably Llama-3.1-8B) with emphasis on running on consumer GPUs. It implements streaming/quantization (NF4), multiple training algorithms and evaluation suites, VRAM probing and model shipping/verification features. The project is published at trysoup.dev and installs without requiring PyTorch, supporting Python 3.10–3.12.

Axolotl is a free, open-source framework for post-training and fine-tuning large language models. It uses YAML configuration to define workflows for preprocessing, training, evaluation, quantization, inference, preference tuning, reinforcement learning, and reward modeling. The project is hosted by axolotl-ai-cloud and documents support for distributed training, mixture-of-experts models, multimodal models, and multiple fine-tuning methods.

MiniMind is an open-source tiny large-language-model project and end-to-end training tutorial developed by Jingyao Gong. Its main dense model is approximately 64M parameters, and the repository provides the model architecture, tokenizer, datasets, inference code, and training pipeline. The pipeline covers pretraining, supervised fine-tuning, hand-written LoRA, DPO, PPO, GRPO, CISPO, model distillation, tool calling, adaptive thinking, and agentic reinforcement learning. Core algorithms are implemented directly with native PyTorch rather than relying on high-level abstractions from third-party training libraries. Its agentic reinforcement-learning path performs multi-turn rollouts, executes generated tool calls, appends tool observations to the context, calculates trajectory-level rewards, and updates the policy; rollout can use local PyTorch generation or an SGLang server. MiniMind supports dense and mixture-of-experts variants, single- and multi-GPU training, YaRN-based RoPE length extrapolation, Transformers-format models, and inference through llama.cpp, vLLM, or Ollama. The repository also includes a Streamlit chat interface and a lightweight OpenAI-compatible API server with tool-call and reasoning fields. It is released under the Apache License 2.0.