gemma-4-31b-it-qat-q4_0-assistant-gguf

PUBLIC

Mirrored

Naive Q4 quant of the QAT MTP drafter for Gemma 4 31B IT QAT, for use with llama.cpp PR 23398

Tasks:image-text-to-textLicense:apache-2.0

imported

huggingface

minio

gguf

quantization

gemma4_assistant

image-text-to-text

base_model:google/gemma-4-31B-it-qat-q4_0-unquantized-assistant

base_model:quantized:google/gemma-4-31B-it-qat-q4_0-unquantized-assistant

license:apache-2.0

endpoints_compatible

region:us

conversational

3downloads0likesLicense:apache-2.0

gemma-4-31b-it-qat-q4_0-assistant.gguf

Naive Q4 quant of the QAT MTP drafter for Gemma 4 31B IT QAT, for use with llama.cpp PR 23398

This model isn't deployed by any Inference Provider yet. Deploy this model →

Format

GGUF

Model size

31B params

image-text-to-text

Mirrored from an external registry.

Last synced 6/14/2026

Base model

No commits available

We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy