view article Article How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications Dharma-AI • 23 days ago • 38
OsaurusAI/Nemotron-3.5-Bolt-74B-A9B-24GB-JANGH2 Image-Text-to-Text • 13B • Updated 28 days ago • 684 • 2
view article Article Accelerating vision-language models with LFM2.5-VL-DSpark LiquidAI • Sep 24 • 51
Running Featured 166 Ternary Bonsai 2 WebGPU Kernels 🌳 166 Run Ternary-Bonsai-2-27B locally in your browser on WebGPU