AtlasAI Center AI tool intelligence
RedHatAI · Open-weight model

gemma 4 31B it FP8 block

gemma 4 31B it FP8 block is a image-text-to-text model published on Hugging Face by RedHatAI.

Downloads (30d)
405,830
Released
Apr 3, 2026
Specifications

gemma 4 31B it FP8 block specs

Provider
RedHatAI
Type
Open-weight model
Model ID
RedHatAI/gemma-4-31B-it-FP8-block
Task
image text to text
Released
Apr 3, 2026
License
apache-2.0
Architecture
transformers
Base model
google/gemma-4-31B-it
Downloads
405,830Hugging Face, last 30 days
Likes
52
Popularity
21/100405,830 Hugging Face downloads in the last 30 days
Source
Hugging Face
Overview

About gemma 4 31B it FP8 block

gemma 4 31B it FP8 block is an open-weight model from RedHatAI, released on Apr 3, 2026, with the apache-2.0 license, 405,830 Hugging Face downloads in the last 30 days.

Specs are sourced from Hugging Face and were last checked on Nov 20, 2026. Always confirm current pricing and limits with the provider before production use.

FP8 weights
FAQ

gemma 4 31B it FP8 block questions

When was gemma 4 31B it FP8 block released?

gemma 4 31B it FP8 block was published on Apr 3, 2026.

Can I run gemma 4 31B it FP8 block locally?

gemma 4 31B it FP8 block is published as an open-weight model on Hugging Face under the apache-2.0 license, so you can download the weights and run them on compatible hardware, subject to the license terms.