CCSSNE
/

gemma-4-26B-A4B-it-heretic-ara-gguf

Mixture of Experts

Model card Files Files and versions

Gemma-4-26B-A4B-It-Heretic-GGUF

Quantized using Unsloth on RTX 4070 Laptop . This version includes the vision adapter (mmproj) and is optimized for local inference.

Downloads last month: 91,849

GGUF

Model size

25B params

Architecture

gemma4

Hardware compatibility

Log In to add your hardware

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for CCSSNE/gemma-4-26B-A4B-it-heretic-ara-gguf

Base model

trohrbaugh/gemma-4-26B-A4B-it-heretic-ara

Quantized

(4)

this model