Swift 1.5 27B Collection Swift 1.5 on Qwen3.8-27B: stronger than Swift 1.0 on agentic and coding tasks, with fewer thinking tokens. BF16 weights and every quant. • 11 items • Updated 7 days ago • 23
Running on Zero Agents Featured 275 Laya Demo 🎯 275 Fast System 1 decisions with calibrated probabilities
prism-ml/Ternary-Bonsai-2-27B-gguf Text Generation • 27B • Updated 19 days ago • 4.79M • 2.69k
Running Featured 152 Ternary Bonsai 2 WebGPU Kernels 🌳 152 Run Ternary-Bonsai-2-27B locally in your browser on WebGPU
litert-community/functiongemma-270m-ft-mobile-actions Text Generation • Updated 1 day ago • 1.36k • 275