nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 Text Generation • 335B • Updated about 17 hours ago • 7.42k • • 94
Running 10 TurboQuant on Consumer GPUs — 100K Context on RTX 3090, 64K on RTX 4070 🚀 10 Extend LLM context to 100K tokens on consumer GPUs
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research Paper • 2605.22878 • Published 17 days ago • 58