TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published 9 days ago • 106
bartowski/google_gemma-4-26B-A4B-it-GGUF Image-Text-to-Text • 25B • Updated 4 days ago • 187k • 87
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 Text Generation • 124B • Updated 4 days ago • 1.02M • 229
Qwen/Qwen3.5-397B-A17B Image-Text-to-Text • 403B • Updated about 1 month ago • 782k • • 1.44k