Qwen2.5-VL-3B-Instruct vs Unlimited-OCR

Specs, VRAM requirements and download trends — updated 10 November 2026.

Qwen · A · Open weights
Params
3.8 B
Context
128,000
30d
1.7 M
baidu · B · Open weights
Params
3.3 B
Context
32,768
30d
5.4 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen2.5-VL-3B-Instruct Unlimited-OCR
Parameters 3.8 B 3.3 B
Architecture Qwen2_5_VLForConditionalGeneration UnlimitedOCRForCausalLM
Context length 128,000 32,768
Licence — mit
Commercial use Unknown Allowed
Languages 1 1
Downloads 30d 1,736,195 5,404,539
Downloads all time 105.4 M 14.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-01-26 2026-06-19

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

7.2 M1.2 M
Qwen2.5-VL-3B-Instruct Unlimited-OCR

VRAM side by side

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

Unlimited-OCR · fp16 15.7 GB / 24 GB
✅ Runs comfortably
Qwen2.5-VL-3B-Instruct · fp16 @ 125K ctx 17.5 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons