gemma-4-31B-it-FP8-block vs UI-TARS-1.5-7B

Specs, VRAM requirements and download trends — updated 5 August 2026.

RedHatAI · A
Params
31.3 B
Context
30d
4.8 M
apache-2.0 · commercial OK
ByteDance-Seed · B
Params
8.3 B
Context
128,000
30d
909 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification gemma-4-31B-it-FP8-block UI-TARS-1.5-7B
Parameters 31.3 B 8.3 B
Architecture Gemma4ForConditionalGeneration Qwen2_5_VLForConditionalGeneration
Context length 128,000
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1
Downloads 30d 4,755,707 909,011
Downloads all time 9.1 M 3.3 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-03 2025-04-16

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

5.7 M909 K
gemma-4-31B-it-FP8-block UI-TARS-1.5-7B

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
❌ Won’t fit
UI-TARS-1.5-7B · fp16 @ 125K ctx 56.4 GB / 24 GB
❌ Won’t fit

Adjacent comparisons