google / image-text-to-text updated 1 year ago

gemma-3-12b-it

Params
12.2 B
Context
Downloads 30d
1.3 M
Likes
797
Commercial use: conditional · gemma Gated — accept licence SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days
1.3 M1.2 M
Jul 28Jul 31Aug 3Aug 6

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 24.4 GB 29.1 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
Gemma3ForConditionalGeneration
Parameters
12.2 B
Tensor type
BF16
Licence
gemma
First seen on the Hub
2025-03-01
Training datasets
undisclosed
Added to our catalog
2026-07-28