RedHatAI / image-text-to-text Open weights updated 2 months ago

gemma-4-26B-A4B-it-FP8-dynamic

Name: gemma-4-26B-A4B-it-FP8-dynamic
Author: RedHatAI

- Model Architecture: Gemma4ForConditionalGeneration - Input: Text / Image - Output: Text - Model Optimizations: - Weight quantization: FP8 - Activation quantization: FP8 - Release Date: 2026-04-04 - Version: 1.0 - Model Developers: RedHatAI

Params

26.5 B

Context

—

Downloads 30d

1.3 M

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 451 K in the last 30 days (50.9%)

1.5 M835 K

Jul 28Sep 1Oct 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f8_e4m3	28.6 GB	36.0 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: Gemma4ForConditionalGeneration
Parameters: 26.5 B
Tensor type: F8_E4M3
Licence: apache-2.0
First seen on the Hub: 2026-04-06
Base model: gemma-4-26B-A4B-it
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base gemma-4-26B-A4B-it google 5.5 M

Compare with any image-text-to-text model

Popular comparisons

Qwen3.8-27B 7.5 M gemma-4-31B-it 7.1 M gemma-4-26B-A4B-it 5.5 M Qwen3.8-27B-FP8 5.3 M Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF 4.9 M Huihui-Qwen3.8-27B-abliterated-GGUF 3.9 M