GStars
    FlashML-org

    FlashML-org/FreeToken

    FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

    deep-learning
    deepseek-v4
    edge
    glm
    inference
    minimax
    Python
    Apache-2.0
    16.6K stars
    1.6K forks
    16.6K GitHub watchers
    Updated Nov 5, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    5 releases in the last 90 days, the latest 56 days ago, with 23 contributors on GitHub.

    Use Cases & Benefits

    • Enables datacenter-scale Mixture-of-Experts model serving on personal and consumer hardware efficiently and at interactive speeds.
    • Delivers fast, elastic, and bandwidth-adaptive runtime for large MoE models using heterogeneous edge resources without engine restarts.
    • Use for running frontier-scale open-weight MoE models locally on gaming PCs or laptops to reduce cloud dependency and latency.
    • Use for integrating large MoE models with Anthropic/OpenAI-compatible APIs to build advanced coding and tool-calling AI agents.
    • Use for dynamically managing VRAM and caching to optimize inference workloads on diverse consumer GPUs including NVIDIA RTX series.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present
    • Contributing guide: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Unlock datacenter-class intelligence on the hardware you already own — Run 290B+ frontier MoE models locally on your gaming PC at blistering interactive speeds.

    Excerpt from the FlashML-org/FreeToken README on GitHub (Apache-2.0 license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Sep 22: +144Sep 23: +105Sep 24: +53Sep 25: +27Nov 3: +656Nov 4: +448Nov 5: +109

    +3,175 stars over 45 days across 11 snapshot days; best day +656 on Nov 3.

    Forks

    1.6K+303

    Open issues

    466+134

    Compared with peers in Deep Learning

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    View category →
    FlashML-org/FreeToken compared with Deep Learning repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    rohitg00/ai-engineering-from-scratch78.3K+1.6K751 day ago
    SYSTRAN/faster-whisper26.5K—40368 days ago
    FlashML-org/FreeToken16.6K—5756 days ago
    GeeeekExplorer/nano-vllm16.3K—12—
    Lightning-AI/litgpt13.8K—58129 days ago
    data-privacy-stack/presidio11.8K—6410 days ago
    Category median16.3K—58—
    Compare FreeToken with ai-engineering-from-scratch, faster-whisper, nano-vllm →

    Discover Repositories

    Search across tracked repositories by name or description