unsloth/gemma-4-12B-it-qat-GGUF
Any-to-Any • 12B • Updated • 1.11M • 446
Gemma 4 QAT
Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy.
Note GGUFs to run:
-
unsloth/gemma-4-26B-A4B-it-qat-GGUF
Image-Text-to-Text • 25B • Updated • 603k • 391 -
unsloth/gemma-4-31B-it-qat-GGUF
Image-Text-to-Text • 31B • Updated • 522k • 180 -
unsloth/gemma-4-E4B-it-qat-GGUF
Any-to-Any • 7B • Updated • 510k • 161 -
unsloth/gemma-4-E2B-it-qat-GGUF
Any-to-Any • 5B • Updated • 431k • 72 -
unsloth/gemma-4-E2B-it-qat-mobile-GGUF
Any-to-Any • 5B • Updated • 35.3k • 37 -
unsloth/gemma-4-E4B-it-qat-mobile-GGUF
Any-to-Any • 7B • Updated • 14.1k • 28 -
unsloth/gemma-4-26B-A4B-it-qat-q4_0-unquantized
Image-Text-to-Text • 27B • Updated • 1.8k • 3
unsloth/gemma-4-E2B-it-qat-q4_0-unquantized
Any-to-Any • 5B • Updated • 2.43k • 4Note BF16 Safetensor:
-
unsloth/gemma-4-E4B-it-qat-q4_0-unquantized
Any-to-Any • 8B • Updated • 1.35k • 3 -
unsloth/gemma-4-12B-it-qat-q4_0-unquantized
Any-to-Any • 12B • Updated • 3.23k • 9 -
unsloth/gemma-4-31B-it-qat-q4_0-unquantized
Image-Text-to-Text • 33B • Updated • 438 • • 4 -
unsloth/gemma-4-E2B-it-qat-mobile
Any-to-Any • 2B • Updated • 386 • 4 -
unsloth/gemma-4-E4B-it-qat-mobile
Any-to-Any • 3B • Updated • 307 • 4 -
unsloth/gemma-4-E4B-it-qat-w4a16
Any-to-Any • 9B • Updated • 4.57k • 3 -
unsloth/gemma-4-E2B-it-qat-w4a16
Any-to-Any • 6B • Updated • 410 • 3