← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

gufo

github.com

The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1,801.01 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2

Open source

Visit github.comexternal siteGitHub1,103 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. FlashQwen

    A from-scratch CUDA inference engine for Qwen3

    github.comOpen sourcelatest reaction

    Hacker News
    5 pts
    Product Hunt
    No reaction
    GitHub
    No reaction

  2. halogen-flash-server

    Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    Product Hunt
    No reaction
    GitHub
    1,253 stars

  3. Qwen 3.5 running on a $300 Android phone

    on-device, open source

    github.comDesktopMobileOpen source4 reactionslatest reaction

    Hacker News
    124 pts
    Product Hunt
    No reaction
    GitHub
    3,346 stars

  4. Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s

    Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

    github.comCLILibraryDesktopOpen source2 reactionslatest reaction

    Hacker News
    240 pts
    Product Hunt
    No reaction
    GitHub
    656 stars

  5. Qwen3.8-Flash-Next

    The open-weight preview of Qwen4

    qwen.ai11 reactionslatest reaction

    Hacker News
    No reaction
    Product Hunt
    315 votes
    GitHub
    No reaction