surya-ocr-2 vs Gemma-4-E4B-Uncensored-HauhauCS-Aggressive

Specs, VRAM requirements and download trends — updated 21 September 2026.

datalab-to · A
Params
690 M
Context
30d
1.2 M
openrail licence · conditional
HauhauCS · B
Params
Context
30d
1.8 M
gemma licence · conditional

Specification comparison

Differences are highlighted; identical values are muted.

Specification surya-ocr-2 Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Parameters 690 M
Architecture Qwen3_5ForConditionalGeneration
Context length
Licence openrail gemma
Commercial use Conditional Conditional
Languages 2
Downloads 30d 1,197,682 1,842,501
Downloads all time 3.6 M 6.9 M
Quantizations on the Hub SAFETENSORS GGUF
Gated No No
First seen on the Hub 2026-05-14 2026-04-02

Download trend

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

2.7 M873 K
surya-ocr-2 Gemma-4-E4B-Uncensored-HauhauCS-Aggressive

VRAM side by side

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

surya-ocr-2 · fp16 2.1 GB / 24 GB
✅ Runs comfortably
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive · Q4_K_M 6.4 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons