Skip to main content
Google
Gemma 4 31B IT
Model
Google
Gemma 4 31B IT

Gemma 4 31B IT is a dense multimodal decoder-only transformer in the Eevee / Gemma 4 family designed for reasoning, coding assistance, multimodal understanding, and agentic workflows

  • 13 Versions
    bf16-64k400-tp2-config-nospec-mml-nofp8-rpSigned
    08/26/2026 7:22 PM UTC275 B
    hf-52f3f65b-qat-w4a16ctSigned
    08/26/2026 7:22 PM UTC21.7 GB
    nvfp4-5k500-tp1-config-rpSigned
    08/26/2026 7:22 PM UTC373 B
    nvfp4-8k1k-tp4-config-nospec-rpSigned
    08/26/2026 7:22 PM UTC341 B
    bf16-5k500-tp4-config-nospec-rpSigned
    08/26/2026 7:22 PM UTC216 B
    nvfp4-64k400-tp4-config-nospec-rpSigned
    08/26/2026 7:22 PM UTC341 B
    bf16-8k1k-tp1-config-mml-rpSigned
    08/26/2026 7:22 PM UTC488 B
    nvfp4-5k500-tp2-config-gmu85-rpSigned
    08/26/2026 7:22 PM UTC403 B
    int4-5k500-tp2-config-rpSigned
    08/26/2026 7:22 PM UTC391 B
    hf-ba74f5b-nimSigned
    06/01/2026 7:44 PM UTC58.28 GB

    NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.