metadata
license: apache-2.0
base_model: coder3101/gemma-4-E4B-it-heretic
pipeline_tag: any-to-any
tags:
- gguf
- llama-cpp
- gemma-4
- any-to-any
gemma-4-E4B-it-heretic-GGUF
This repository contains GGUF format quantizations of coder3101/gemma-4-E4B-it-heretic.
Quantizations Provided
The following quantization formats have been provided to accommodate various hardware setups:
- Q8_0: Very high quality, near-unquantized performance.
- Q6_K: High quality, excellent balance of size and performance.
- Q5_K_M: Good quality, slightly smaller footprint.
- Q4_K_M: Standard medium quantization, optimal for general use.
- Q3_K_M: Maximum compression for tight VRAM/RAM constraints.