Gemma 4 QAT Collection Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated about 18 hours ago • 44
unsloth/gemma-4-26B-A4B-it-qat-GGUF Image-Text-to-Text • 25B • Updated about 15 hours ago • 28.4k • 62
deployed-models Collection Models that are currently deployed by the hf-inference provider • 1527 items • Updated about 1 hour ago • 40
TIPSv2 Collection TIPSv2 foundational vision-language models. Webpage: https://gdm-tipsv2.github.io/ • 9 items • Updated Apr 14 • 35
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16 Text Generation • 561B • Updated 1 day ago • 794 • 22
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 Text Generation • 561B • Updated about 7 hours ago • 47.3k • 145
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 Text Generation • 335B • Updated about 7 hours ago • 17.2k • • 119
Running on CPU Upgrade MCP 3 Reachy Mini Search Tool 🔍 3 Public MCP canary Space for Reachy Mini remote tools.