view article Article The Fast Gemma Challenge: our verified-SOTA recipe, in full FINAL-Bench • Aug 3 • 24
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B Text Generation • 33B • Updated Feb 24, 2025 • 464k • • 1.63k
meta-llama/Llama-4-Scout-17B-16E-Instruct Image-Text-to-Text • 109B • Updated May 22, 2025 • 180k • • 1.36k
nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct Text Generation • 8B • Updated Apr 17, 2025 • 489 • • 128
meta-llama/Llama-3.1-8B-Instruct Text Generation • 8B • Updated Sep 25, 2024 • 6.08M • • 8.01k