Qwen3-8B vs Qwen2.5-3B

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

Qwen · A
Params
8.2 B
Context
40,960
30d
16.3 M
apache-2.0 · commercial OK
Qwen · B
Params
3.1 B
Context
32,768
30d
310 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-8B Qwen2.5-3B
Parameters 8.2 B 3.1 B
Architecture Qwen3ForCausalLM Qwen2ForCausalLM
Context length 40,960 32,768
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages 1
Downloads 30d 16,272,885 310,086
Downloads all time 103.2 M 6.7 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2024-09-15

Download trend

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

16.6 M297 K
Qwen3-8B Qwen2.5-3B

VRAM side by side

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

Qwen2.5-3B · fp16 7.8 GB / 24 GB
✅ Runs comfortably
Qwen3-8B · fp16 19.7 GB / 24 GB
⚠️ Tight — reduce context

Adjacent comparisons