Qwen2-VL-2B-Instruct vs Qwen3.5-2B

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

Qwen · A
Params
2.2 B
Context
32,768
30d
3.0 M
apache-2.0 · commercial OK
Qwen · B
Params
2.3 B
Context
30d
2.6 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen2-VL-2B-Instruct Qwen3.5-2B
Parameters 2.2 B 2.3 B
Architecture Qwen2VLForConditionalGeneration Qwen3_5ForConditionalGeneration
Context length 32,768
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1
Downloads 30d 2,999,059 2,645,919
Downloads all time 46.0 M 10.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-08-28 2026-02-28

Download trend

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

3.1 M2.4 M
Qwen2-VL-2B-Instruct Qwen3.5-2B

VRAM side by side

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

Qwen2-VL-2B-Instruct · fp16 5.7 GB / 24 GB
✅ Runs comfortably
Qwen3.5-2B · fp16 5.8 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons