Alternatives to Unsloth

Ollama runs open models locally or through per-token cloud inference, with an OpenAI-compatible API endpoint.

LM Studio runs open LLMs locally with llama.cpp and MLX, then hands your files to the Bionic agent for document editing, coding and

vLLM turns open-weight LLMs into high-throughput, OpenAI-compatible inference endpoints on your own GPUs.

AgenticSeek is a fully local, open-source AI assistant that browses the web, writes and runs code, and plans multi-step tasks on your own machine.

Podman AI Lab runs open source LLMs locally with a model catalog, Kubernetes-ready recipes and OpenAI-compatible endpoints.

Olares is an open-source personal AI cloud OS that runs local LLMs, agents, and self-hosted apps on hardware you own.

Jan runs open models like Llama, Qwen and DeepSeek locally on your desktop, free and open source.

Offline AI chat on iPhone, iPad, and Mac that runs open-source LLMs on-device via Core ML — no cloud, no data collection.

Free, open-source local AI server that runs LLMs, image, music, video and 3D generation entirely on your Apple Silicon Mac.

Free OpenClaw Book: a 45-chapter GitBook on how the OpenClaw AI assistant works, down to the source line

Apple Silicon ML platform for training, serving, quantizing, and merging local models on M1–M5 Macs.

Open-source JavaScript library that runs small LLMs like Llama 3.2 1B Instruct inside the browser via WebAssembly and WebGPU.

RWKV Runner: free open-source desktop app to run and fine-tune infinite-context RWKV models locally

On-device AI inference SDKs with hand-tuned MetalRT and QHexRT kernels, plus Wally's hosted open-model API.

Atomic Agent is an open-source local AI agent that runs a quantized LLM on your own GPU and controls your browser, files and shell with no

BitNet (bitnet.cpp): Microsoft's open-source 1-bit LLM inference framework for fast, lossless CPU and GPU inference

picoLLM runs quantized LLMs fully on-device — local inference for phones, embedded Linux, and microcontrollers with no cloud calls.

Atomic Chat runs 1,000+ open models fully offline on Mac, Windows, Linux or phone — no account, no message caps.

Benchmark local LLM tokens-per-second through Ollama with one CLI command and a public results table.

Runs open-source AI models entirely on your iPhone or Mac — chat, offline voice, document Q&A, and no account required.

Open-source, local-first terminal assistant that turns plain English into shell commands and runs fully offline through Ollama.

Open-source browser extension that runs AI models on your own machine through Ollama — chat, tab context, agent mode, and page translation with nothing sent to

A headless React hooks library that runs Vicuna-13B chat entirely in your browser via WebGPU, with no prompt or completion leaving the client.

Open-source compiler and deployment engine for running LLMs natively on web, mobile, desktop and cloud

Free LLM RAM calculator that sizes the largest quantized model your memory budget can hold

AI research lab building tiny sub-1 MB models that run on microcontrollers and edge devices.

A free, open-source app that runs small Llama and DeepSeek models entirely on your Apple device, with no internet needed after download.

Osaurus runs local AI agents on your Mac — MIT-licensed, model-agnostic, and fully offline when you want it.

LFM2.5 is Liquid AI's open-weight on-device model family for local text, vision, and speech AI on phones, vehicles, and NPUs.

Flowly is a private-memory personal AI agent that runs on your own API keys across macOS, iOS and Android.