Qwen3.5-0.8B vs surya-ocr-2
Specs, VRAM requirements and download trends — updated 10 November 2026.
datalab-to · B · Open weights
Params
690 M
Context
—
30d
975 K
openrail licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.5-0.8B | surya-ocr-2 |
|---|---|---|
| Parameters | 870 M | 690 M |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | openrail |
| Commercial use | Allowed | Conditional |
| Languages | — | — |
| Downloads 30d | 3,549,829 | 975,415 |
| Downloads all time | 23.7 M | 5.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-28 | 2026-05-14 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
3.8 M975 K
Qwen3.5-0.8B
surya-ocr-2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
surya-ocr-2 · fp16
2.1 GB / 24 GB
Qwen3.5-0.8B · fp16
2.6 GB / 24 GB