gemma-4-26B-A4B-it-AWQ-4bit
Hugging Face GitHub Launch Blog Documentation Technical Report License: Apache 2.0 Authors: Google DeepMind
Params
25.8 B
Context
—
Downloads 30d
1.1 M
Likes
111
Download history
daily snapshots · 106 days
▲ 185 K in the last 30 days (19.4%)
1.1 M830 K
Oct 12Oct 22Nov 1Nov 10
2.8 M830 K
Aug 13Sep 12Oct 12Nov 10
4.5 M830 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 | i32 | 17.2 GB | 23.3 GB | ⚠️ Tight — reduce context |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Gemma4ForConditionalGeneration
- Parameters
- 25.8 B
- Tensor type
- I32
- Licence
- apache-2.0
- First seen on the Hub
- 2026-04-03
- 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.
Compare with any image-text-to-text model