Every option in the catalog for when you need to run a model on your own machine, fully offline — 19 local LLM runners, 19 of them free or freemium, with the pricing tier printed on every row.
Flocci AI Tools lists 19 of them, ordered free tiers first: AnythingLLM, BitNet, exo, Google AI Edge Gallery and GPT4All. Every one of them is free or has a free tier. Each entry states what it uniquely does rather than a score.
18 on this page are marked fully free with no paid plan at all: AnythingLLM, BitNet, exo, Google AI Edge Gallery and GPT4All. The remaining 1 are freemium, trial or paid, and each is labelled with its exact tier so nothing surprises you at sign-up.
Free tools first, then freemium, then trial, then paid, and alphabetically inside each tier. Nobody pays to appear higher: Flocci AI Tools carries no ads, no sponsored slots and no paid listings, so the order reflects price and nothing else.
AnythingLLM, Google AI Edge Gallery, KoboldCpp, MediaPipe (Google AI Edge) and MLC LLM have an iOS or Android app. 5 of the 19 free local LLM runners here can run on your phone.
AnythingLLM, BitNet, exo, Google AI Edge Gallery and GPT4All can be self-hosted or run locally without a browser — useful for privacy, air-gapped networks, or avoiding API rate limits. 16 of the 19 free local LLM runners here run offline.
| Tool | Pricing | Type | Listed for |
|---|---|---|---|
| AnythingLLM | Free | Local LLM Runners | All-in-one local RAG and agents app |
| BitNet | Free | Local LLM Runners | Official inference framework for 1-bit (ternary) LLMs |
| exo | Free | Local LLM Runners | Links everyday devices (Macs, PCs, phones) into one cluster to run models too large for a single machine |
| Google AI Edge Gallery | Free | Local LLM Runners | Runs Gemma models fully on-device on Android and iOS, offline after one model download |
| GPT4All | Free | Local LLM Runners | Private local chat with your documents |
| Jan | Free | Local LLM Runners | Open-source, offline ChatGPT alternative |
| KoboldCpp | Free | Local LLM Runners | Ships as a single portable executable with a bundled web UI (KoboldAI Lite) |
| llama.cpp | Free | Local LLM Runners | Pure C/C++ inference engine with minimal dependencies, runs on CPU-only hardware |
| llamafile | Free | Local LLM Runners | Packs model weights and runtime into one executable that runs on macOS, Windows and Linux |
| LM Studio | Free | Local LLM Runners | Polished desktop GUI for local models |
| LocalAI | Free | Local LLM Runners | Drop-in OpenAI-compatible API server running models on your own hardware, CPU or GPU |
| MediaPipe (Google AI Edge) | Free | Local LLM Runners | Cross-platform on-device ML for vision, audio, text and LLM inference |
| MLC LLM | Free | Local LLM Runners | Compiles and runs LLMs natively on iOS, Android, browsers (WebGPU), Mac, Windows and Linux |
| MLX-LM (Apple) | Free | Local LLM Runners | Purpose-built for Apple Silicon's unified memory architecture, faster than llama.cpp for many models on Mac |
| Ollama | Free | Local LLM Runners | The default way to run LLMs locally |
| Open WebUI | Free | Local LLM Runners | Self-hosted ChatGPT-style interface |
| SGLang | Free | Local LLM Runners | RadixAttention for automatic prefix-cache reuse across requests |
| vLLM | Free | Local LLM Runners | PagedAttention memory management for high-throughput multi-request GPU serving |
| Msty | Freemium | Local LLM Runners | Nexus module: unified gateway for managing model connections, credentials and usage policy across providers |