Running on CPU Upgrade Featured 3.33k The Smol Training Playbook π 3.33k The secrets to building world-class LLMs
deepseek-ai/DeepSeek-V3.1-Terminus Text Generation β’ 685B β’ Updated Sep 29, 2025 β’ 18k β’ β’ 380
Alibaba-NLP/Tongyi-DeepResearch-30B-A3B Text Generation β’ 31B β’ Updated Oct 10, 2025 β’ 7.91k β’ 826
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 Text Generation β’ 50B β’ Updated Oct 15, 2025 β’ 99.4k β’ 239
Running Agents 76 KVPress Leaderboard π₯ 76 KVPress leaderboard: benchmark KV Cache compression methods