PrunedHub-Qwen3-30B-A3B-EN-80pct-MxMoE
30B open-weight LLM by GOBA-AI-Labs
Live
Open / InstallLast updated October 29, 2026
Description
PrunedHub-Qwen3-30B-A3B-EN-80pct-MxMoE is an open-weight text-generation model with roughly 30B parameters published by GOBA-AI-Labs on the Hugging Face Hub. It has 459 downloads. Runs with gguf.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
GOBA-AI-Labs
Platform
api
Pricing model
free
Categories
- Productivity
Tags
- moe
- mixture-of-experts
- pruned
- expert-pruning
- mixed-quantization
- mxmoe
- qwen3
- language-aware-pruning
Capabilities
- Text generation
- Conversational
- GGUF quantised builds
- Library: gguf
- 30B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 25, 2026