Qwen3-VL-4B-Instruct vs Phi-3.5-vision-instruct

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

Qwen · A
Params
4.4 B
Context
30d
4.0 M
apache-2.0 · commercial OK
microsoft · B
Params
4.2 B
Context
131,072
30d
1.3 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-VL-4B-Instruct Phi-3.5-vision-instruct
Parameters 4.4 B 4.2 B
Architecture Qwen3VLForConditionalGeneration Phi3VForCausalLM
Context length 131,072
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages 1
Downloads 30d 3,998,087 1,309,583
Downloads all time 21.1 M 19.0 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-10-11 2024-08-16

Download trend

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

4.0 M1.2 M
Qwen3-VL-4B-Instruct Phi-3.5-vision-instruct

VRAM side by side

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

Qwen3-VL-4B-Instruct · fp16 10.9 GB / 24 GB
✅ Runs comfortably
Phi-3.5-vision-instruct · fp16 @ 128K ctx 19.6 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons