← 최신 프로덕트

I benchmarked Gemma 4 E2B

the 2B model beat the 12B on multi-turn. Gemma 4 E2B scored 80.4% across 9 enterprise suites — 0.4 points behind the previous-gen 4B model. But the real surprise: 70% multi-turn, the highest score in the entire Gemma family.

aiexplr.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Running Gemma-4 26B at 124 tokens/SEC on a CPU, no GPU

    apeg.dev

    Gemma-4 26B at 124 tokens/sec on a desktop CPU, no GPU. The byte budget, the quantization recipe, the roofline, and the failed attempts, measured.

    Hacker News10점

  2. Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

    github.com

    Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

    Hacker News919점

  3. Gemma Gem

    github.com

    AI model embedded in a browser – no API keys, no cloud

    Hacker News156점

  4. Cactus Hybrid

    github.com

    We taught Gemma 4 to know when it's wrong

    Hacker News191점

  5. Gemma 4 Multimodal Fine-Tuner for Apple Silicon

    github.com

    Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.

    Hacker News235점