deepseek-ai/DeepSeek-V4-Flash-0731 Text Generation β’ 304B β’ Updated 1 day ago β’ 156k β’ β’ 1.53k
view post Post 4662 Weβre releasing Gemma 4 NVFP4 quants that run 1.5Γ faster on your GPU.Gemma-4-12B NVFP4 works on 11GB VRAM.26B-A4B hits 13K tok/s (B200).Unsloth NVFP4 enables faster, more accurate 4-bit Blackwell inference.Blog: https://unsloth.ai/docs/basics/nvfp4Gemma NVFP4: https://huggingface.co/collections/unsloth/nvfp4 See translation 3 replies Β· π₯ 12 12 π€ 3 3 π 2 2 π 2 2 + Reply
DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 β’ 15 items β’ Updated Mar 10 β’ 720