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
liked a model about 20 hours ago
commaai/openpilot_driving_models liked a model about 22 hours ago
zai-org/GLM-5.3-Flash liked a model 6 days ago
RedHatAI/GLM-5.3-Flash-NVFP4Organizations
None yet
models 22
yasu-oh/gemma-4-26B-A4B-it-qat-NVFP4
Image-Text-to-Text • Updated • 31
yasu-oh/gemma-4-12B-it-qat-NVFP4
Image-Text-to-Text • 12B • Updated • 89 • 1
yasu-oh/gemma-4-E2B-it-qat-NVFP4
Image-Text-to-Text • 5B • Updated • 79
yasu-oh/gemma-4-E4B-it-qat-NVFP4
Image-Text-to-Text • Updated • 22
yasu-oh/gemma-4-31B-it-qat-NVFP4
Image-Text-to-Text • 18B • Updated • 97 • 1
yasu-oh/Qwen3-Reranker-0.6B
Text Ranking • 0.6B • Updated • 14
yasu-oh/pplx-embed-v1-0.6b
Feature Extraction • 0.6B • Updated • 18
yasu-oh/Magistral-Small-2506-GGUF
Text Generation • 24B • Updated • 62
yasu-oh/Llama-3-Swallow-Infused-R1776-70B
Text Generation • 71B • Updated • 21 • 1
yasu-oh/Llama-3-SS-Infused-R1776-70B
Text Generation • 71B • Updated • 14 • 1
datasets 0
None public yet