surya-ocr-2 vs Huihui-Qwen3.8-27B-abliterated-GGUF

Specs, VRAM requirements and download trends — updated 18 September 2026.

datalab-to · A
Params
690 M
Context
30d
1.2 M
openrail licence · conditional
huihui-ai · B
Params
27.0 B
Context
30d
2.6 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification surya-ocr-2 Huihui-Qwen3.8-27B-abliterated-GGUF
Parameters 690 M 27.0 B
Architecture Qwen3_5ForConditionalGeneration
Context length
Licence openrail apache-2.0
Commercial use Conditional Allowed
Languages
Downloads 30d 1,197,682 2,623,928
Downloads all time 3.6 M 3.2 M
Quantizations on the Hub SAFETENSORS GGUF
Gated No No
First seen on the Hub 2026-05-14 2026-08-16

Download trend

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

2.9 M873 K
surya-ocr-2 Huihui-Qwen3.8-27B-abliterated-GGUF

VRAM side by side

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

surya-ocr-2 · fp16 2.1 GB / 24 GB
✅ Runs comfortably
Huihui-Qwen3.8-27B-abliterated-GGUF · Q4_K 23.0 GB / 24 GB
⚠️ Tight — reduce context

Adjacent comparisons