Qwen2.5-3B-Instruct vs PowerLM-3b

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

Qwen · A
Params
3.1 B
Context
32,768
30d
6.0 M
ibm-research · B
Params
3.5 B
Context
4,096
30d
203 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen2.5-3B-Instruct PowerLM-3b
Parameters 3.1 B 3.5 B
Architecture Qwen2ForCausalLM GraniteForCausalLM
Context length 32,768 4,096
Licence other apache-2.0
Commercial use Unknown Allowed
Languages 1
Downloads 30d 5,952,246 202,930
Downloads all time 110.0 M 1.1 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-09-17 2024-08-14

Download trend

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

6.0 M195 K
Qwen2.5-3B-Instruct PowerLM-3b

VRAM side by side

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

Qwen2.5-3B-Instruct · fp16 7.8 GB / 24 GB
✅ Runs comfortably
PowerLM-3b · fp16 16.5 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons