noctrex/gemma-4-26B-A4B-it-MXFP4_MOE-GGUF

These are MXFP4 quantizations of the model gemma-4-26B-A4B-it

Quick Start

1. Download the latest release of llama.cpp.
2. Download your preferred model variant from below.
3. For the mmproj file, it is recommended to use the F32 version for the best visual processing results. F32 > BF16 > F16

Which version should I choose?

All variants use MXFP4 for the MoE (Mixture of Experts) weights to keep the model efficient. The difference lies in how the remaining tensors are handled:

Variant	Quality	Performance	Recommendation
BF16	⭐⭐⭐ (Highest)	Variable*	Best for maximum accuracy; original unquantized weights.
F16	⭐⭐ (High)	Fast	Great alternative if BF16 is slow on your hardware.
Q8	⭐ (Standard)	Fastest	Balanced performance and memory usage.

*Note: On some older architectures, BF16 may be slower than F16.

As per danielhanchen, I also updated the models. Please re-download them.