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

Specs, VRAM requirements and download trends — updated 6 August 2026.

Qwen · A
Params
3.8 B
Context
128,000
30d
8.2 M
zai-org · B
Params
1.3 B
Context
30d
3.8 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen2.5-VL-3B-Instruct GLM-OCR
Parameters 3.8 B 1.3 B
Architecture Qwen2_5_VLForConditionalGeneration GlmOcrForConditionalGeneration
Context length 128,000
Licence mit
Commercial use Unknown Allowed
Languages 1 8
Downloads 30d 8,170,451 3,769,294
Downloads all time 97.0 M 28.1 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-01-26 2026-01-30

Download trend

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

8.2 M3.6 M
Qwen2.5-VL-3B-Instruct GLM-OCR

VRAM side by side

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

GLM-OCR · fp16 3.6 GB / 24 GB
✅ Runs comfortably
Qwen2.5-VL-3B-Instruct · fp16 @ 125K ctx 17.5 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons