Qwen3.6-27B-FP8 vs surya-ocr-2

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

Qwen · A

Params

27.8 B

Context

—

30d

7.8 M

apache-2.0 · commercial OK

datalab-to · B

Params

690 M

Context

—

30d

1.2 M

openrail licence · conditional

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3.6-27B-FP8	surya-ocr-2
Parameters	27.8 B	690 M
Architecture	Qwen3_5ForConditionalGeneration	Qwen3_5ForConditionalGeneration
Context length	—	—
Licence	apache-2.0	openrail
Commercial use	Allowed	Conditional
Languages	—	—
Downloads 30d	7,781,120	1,158,004
Downloads all time	23.4 M	1.6 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-04-21	2026-05-14

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

7.8 M873 K

Qwen3.6-27B-FP8 surya-ocr-2

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

surya-ocr-2 · fp16 2.1 GB / 24 GB

✅ Runs comfortably

Qwen3.6-27B-FP8 · fp16 38.6 GB / 24 GB

❌ Won’t fit