granite-4.2-3b-MXFP4A16-GPTQ
3B open-weight LLM by quark75
Live
Open / InstallLast updated October 23, 2026
Description
granite-4.2-3b-MXFP4A16-GPTQ is an open-weight text-generation model with roughly 3B parameters published by quark75 on the Hugging Face Hub. It has 472 downloads. Runs with transformers.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
quark75
Platform
api
Pricing model
free
Categories
- Productivity
Tags
- granite
- text-generation
- mxfp4
- mx-format
- llama.cpp
- gptq
- compressed-tensors
- llmcompressor
Capabilities
- Text generation
- Conversational
- GGUF quantised builds
- Library: transformers
- 3B parameters
Information
TypeLarge Language Model
Model TypeText Generation
SourceHuggingface Models
AddedOctober 12, 2026