gemma-4-31B-it vs SmolVLM-256M-Instruct

Specs, VRAM requirements and download trends — updated 28 July 2026.

google · A
Params
32.7 B
Context
30d
9.0 M
apache-2.0 · commercial OK
HuggingFaceTB · B
Params
260 M
Context
30d
872 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification gemma-4-31B-it SmolVLM-256M-Instruct
Parameters 32.7 B 260 M
Architecture Gemma4ForConditionalGeneration Idefics3ForConditionalGeneration
Context length
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1
Downloads 30d 9,044,229 871,636
Downloads all time 59.5 M 7.5 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-03-11 2025-01-17

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

12.4 M872 K
gemma-4-31B-it SmolVLM-256M-Instruct

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

SmolVLM-256M-Instruct · fp16 1.1 GB / 24 GB
✅ Runs comfortably
gemma-4-31B-it · fp16 74.2 GB / 24 GB
❌ Won’t fit

Adjacent comparisons