Gemma 4 QAT models quantized to NVFP4 with GPTQ+iMatrix and FP8-calibrated KV cache using multilingual and tool-use data.
Yasuhiro Ohno
yasu-oh
AI & ML interests
None yet
Recent Activity
updated a model about 15 hours ago
yasu-oh/gemma-4-26B-A4B-it-qat-NVFP4 updated a model about 23 hours ago
yasu-oh/gemma-4-12B-it-qat-NVFP4 updated a model about 24 hours ago
yasu-oh/gemma-4-E2B-it-qat-NVFP4Organizations
None yet