qev Collection Tiny local decision models by Labqoat: calibrated answers in one forward pass, on NVIDIA, Mac and llama.cpp. • 7 items • Updated 14 days ago
squad-0.8b · MoQLE Collection A team of models on your device: qev-0.8b + a router + 2-bit LoRA experts (games, e2e). Mixture of Quantized LoRA Experts. • 4 items • Updated 14 days ago