PowerMoE-3b vs Qwen3-30B-A3B-Instruct-2507-AWQ-4bit

Specs, VRAM requirements and download trends — updated 30 July 2026.

ibm-research · A
Params
3.4 B
Context
4,096
30d
1.2 M
apache-2.0 · commercial OK
cyankiwi · B
Params
5.3 B
Context
262,144
30d
204 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification PowerMoE-3b Qwen3-30B-A3B-Instruct-2507-AWQ-4bit
Parameters 3.4 B 5.3 B
Architecture GraniteMoeForCausalLM Qwen3MoeForCausalLM
Context length 4,096 262,144
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 1,181,539 204,079
Downloads all time 11.9 M 3.0 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2024-08-14 2025-07-29

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

1.8 M204 K
PowerMoE-3b Qwen3-30B-A3B-Instruct-2507-AWQ-4bit

VRAM side by side

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

PowerMoE-3b · fp16 15.9 GB / 24 GB
✅ Runs comfortably
Qwen3-30B-A3B-Instruct-2507-AWQ-4bit · fp16 @ 256K ctx 45.9 GB / 24 GB
❌ Won’t fit

Adjacent comparisons