Qwen3-4B vs Phi-3-vision-128k-instruct

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

Qwen · A
Params
4.0 B
Context
40,960
30d
4.6 M
apache-2.0 · commercial OK
microsoft · B
Params
4.2 B
Context
131,072
30d
238 K
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-4B Phi-3-vision-128k-instruct
Parameters 4.0 B 4.2 B
Architecture Qwen3ForCausalLM Phi3VForCausalLM
Context length 40,960 131,072
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages 1
Downloads 30d 4,598,181 238,418
Downloads all time 70.7 M 3.6 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2024-05-19

Download trend

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

4.6 M231 K
Qwen3-4B Phi-3-vision-128k-instruct

VRAM side by side

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

Qwen3-4B · fp16 10.0 GB / 24 GB
✅ Runs comfortably
Phi-3-vision-128k-instruct · fp16 @ 128K ctx 19.6 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons