Qwen3-4B vs Qwen2.5-7B-Instruct-AWQ

Specs, VRAM requirements and download trends — updated 9 September 2026.

Qwen · A
Params
4.0 B
Context
40,960
30d
6.3 M
apache-2.0 · commercial OK
Qwen · B
Params
7.6 B
Context
32,768
30d
3.6 M
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-4B Qwen2.5-7B-Instruct-AWQ
Parameters 4.0 B 7.6 B
Architecture Qwen3ForCausalLM Qwen2ForCausalLM
Context length 40,960 32,768
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1
Downloads 30d 6,283,681 3,593,565
Downloads all time 78.0 M 21.5 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2024-09-17

Download trend

Daily snapshots, last 44 days (28 Jul – 9 Sep)

6.4 M3.6 M
Qwen3-4B Qwen2.5-7B-Instruct-AWQ A overtook B on 14 Aug

VRAM side by side

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

Qwen2.5-7B-Instruct-AWQ · fp16 7.8 GB / 24 GB
✅ Runs comfortably
Qwen3-4B · fp16 10.0 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons