gemma-4-26B-A4B-it-AWQ-4bit vs deepseek-vl2-tiny

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

cyankiwi · A · Open weights
Params
25.8 B
Context
—
30d
1.1 M
apache-2.0 · commercial OK
deepseek-ai · B · Open weights
Params
3.4 B
Context
—
30d
828 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification gemma-4-26B-A4B-it-AWQ-4bit deepseek-vl2-tiny
Parameters 25.8 B 3.4 B
Architecture Gemma4ForConditionalGeneration —
Context length — —
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages — —
Downloads 30d 1,141,607 828,272
Downloads all time 21.7 M 6.1 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-03 2024-12-13

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

2.8 M828 K
gemma-4-26B-A4B-it-AWQ-4bit deepseek-vl2-tiny

VRAM side by side

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

deepseek-vl2-tiny · fp16 8.4 GB / 24 GB
✅ Runs comfortably
gemma-4-26B-A4B-it-AWQ-4bit · fp16 23.3 GB / 24 GB
⚠️ Tight — reduce context

Adjacent comparisons