gemma-4-26B-A4B-it vs gemma-4-31B-it-FP8-block
Specs, VRAM requirements and download trends — updated 16 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gemma-4-26B-A4B-it | gemma-4-31B-it-FP8-block |
|---|---|---|
| Parameters | 26.5 B | 31.3 B |
| Architecture | Gemma4ForConditionalGeneration | Gemma4ForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 10,031,000 | 936,323 |
| Downloads all time | 61.6 M | 10.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-03-11 | 2026-04-03 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
13.0 M936 K
gemma-4-26B-A4B-it
gemma-4-31B-it-FP8-block
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gemma-4-31B-it-FP8-block · fp16
41.8 GB / 24 GB
gemma-4-26B-A4B-it · fp16
61.3 GB / 24 GB