Qwen2.5-VL-3B-Instruct vs Qwen3-VL-8B-Instruct-FP8

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

Qwen · A
Params
3.8 B
Context
128,000
30d
8.2 M
Qwen · B
Params
8.8 B
Context
30d
3.2 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen2.5-VL-3B-Instruct Qwen3-VL-8B-Instruct-FP8
Parameters 3.8 B 8.8 B
Architecture Qwen2_5_VLForConditionalGeneration Qwen3VLForConditionalGeneration
Context length 128,000
Licence apache-2.0
Commercial use Unknown Allowed
Languages 1
Downloads 30d 8,170,451 3,235,022
Downloads all time 97.0 M 7.0 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-01-26 2025-10-11

Download trend

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

8.2 M2.8 M
Qwen2.5-VL-3B-Instruct Qwen3-VL-8B-Instruct-FP8

VRAM side by side

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

Qwen3-VL-8B-Instruct-FP8 · fp16 13.5 GB / 24 GB
✅ Runs comfortably
Qwen2.5-VL-3B-Instruct · fp16 @ 125K ctx 17.5 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons