You can deploy this model and start earning money today!

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

Name: gemma-4-26B-A4B-it-MXFP4_MOE-GGUF
Availability: InStock

gguf

image-text-to-text

google/gemma-4-26B-A4B-it

quantized

endpoints_compatible

conversational

Views

No views yet

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

Quick Start

Download the latest release of llama.cpp.
Download your preferred model variant from below.
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	Size	Recommendation
BF16	⭐⭐⭐	Variable*	15.80GiB	Best for maximum accuracy; original unquantized weights.
F16	⭐⭐	Fast	15.80GiB	Great alternative if BF16 is slow on your hardware.
Q8	⭐	Fastest	14.36GiB	Balanced performance and memory usage.

Note: On some older architectures, BF16 may be slower than F16.
Check that your GPU supports native BF16

Read the guide from unsloth in order to set up the model's recommended settings:

The official chat template has been updated from Google. If you do not want to download the model again, you can just tell llama.cpp to use the new chat template.

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

Quick Start

Which version should I choose?

The official chat template has been updated from Google. If you do not want to download the model again, you can just tell llama.cpp to use the new chat template.

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