{"version":"v1","licence":"CC-BY-4.0","id":"freetoken","name":"FreeToken","repo":"FlashML-org/FreeToken","repository_url":"https://github.com/FlashML-org/FreeToken","docs_url":"https://github.com/FlashML-org/FreeToken#readme","description":"Apache-2.0 engine and desktop app for running very large open models on your own NVIDIA GPU, with OpenAI and Anthropic-compatible APIs.","summary":"FreeToken (~16k stars, nightly builds only so far) serves large Mixture-of-Experts models on personal machines by sharing the work between GPU, CPU and memory. A desktop app for Windows and Linux sets it up; on Linux there is also a Python package. It offers OpenAI and Anthropic-compatible APIs for coding agents. Needs an NVIDIA GPU; AMD support is experimental. Its authors' paper reports an 8GB laptop GPU running a 35B model and a gaming desktop a 284B one. Those claims were not tested here. Apache-2.0 and free; each model keeps its own licence.","capabilities":["developer-tools"],"tags":["Self-hosted","Local LLM support","OpenAI-compatible API","GPU inference","Needs a GPU","Python","Desktop app","Linux","Windows","Runs AI locally"],"alternatives":[],"facts":{"runs_locally":{"status":"yes","value":"Yes; serves models from your own machine, by default on 127.0.0.1","source_url":"https://github.com/FlashML-org/FreeToken/blob/main/docs/quickstart.md","checked_at":"2026-11-02","confidence":"high","validation":"documentation_review","modes":["local","self-hosted"],"untrusted_source_quote":"API server is ready to serve on 127.0.0.1:1919"},"code_license":{"status":"yes","value":"Apache-2.0","source_url":"https://github.com/FlashML-org/FreeToken/blob/main/LICENSE","checked_at":"2026-11-02","confidence":"high","validation":"documentation_review","spdx":"Apache-2.0","untrusted_source_quote":"Apache License"},"model_license":{"status":"yes","value":"No bundled weights; each model you load keeps its own licence","source_url":"https://github.com/FlashML-org/FreeToken/blob/main/docs/models.md","checked_at":"2026-11-02","confidence":"high","validation":"documentation_review","spdx":null,"applies":false,"untrusted_source_quote":"FreeToken loads HF safetensors checkpoints directly."},"commercial_use":{"status":"yes","value":"Engine is Apache-2.0; commercial use of a model depends on that model's licence","source_url":"https://github.com/FlashML-org/FreeToken/blob/main/LICENSE","checked_at":"2026-11-02","confidence":"high","validation":"documentation_review","untrusted_source_quote":"Apache License"},"paid_services":{"status":"yes","value":"None required; runs open models on your own hardware","source_url":"https://www.flashml.ai/","checked_at":"2026-11-02","confidence":"medium","validation":"documentation_review","required":[],"optional":[],"untrusted_source_quote":"private and offline"},"hardware":{"status":"partial","value":"NVIDIA RTX 30, 40 or 50 series; the paper's smallest machine is an 8GB laptop GPU; larger models need more; AMD is experimental","source_url":"https://arxiv.org/abs/2608.16157","checked_at":"2026-11-02","confidence":"medium","validation":"documentation_review","cpu_ok":false,"min_vram_gb":8,"min_ram_gb":null,"untrusted_source_quote":"hardware ranging from an 8GB laptop GPU to a single workstation GPU"},"platforms":{"status":"partial","value":"Desktop app for Windows and Linux; the Python package is documented for Linux x86_64; macOS not mentioned","source_url":"https://github.com/FlashML-org/FreeToken#desktop-app","checked_at":"2026-11-02","confidence":"high","validation":"documentation_review","windows":"yes","macos":"unknown","linux":"yes","untrusted_source_quote":"Download FreeToken for Windows or Linux"},"setup":{"status":"yes","value":"Medium; the desktop app sets up the engine, but you need a supported GPU and large model downloads","source_url":"https://github.com/FlashML-org/FreeToken#desktop-app","checked_at":"2026-11-02","confidence":"medium","validation":"documentation_review","level":"medium","untrusted_source_quote":"It sets the engine up for you"}},"metrics":{"stars":16076,"forks":1586,"contributors":22,"archived":false,"last_push_at":"2026-11-02T23:05:18Z","latest_release":{"tag":"v0.2.1","published_at":"2026-10-26T03:24:21Z"},"fetched_at":"2026-11-03T01:20:55.050Z"},"url":"https://repoquarry.dev/projects/freetoken","note":"Installation guidance: follow docs_url. This service never installs or runs code."}