labqoat/squad-0.8b
Image-Text-to-Text • 0.9B • Updated • 48
squad-0.8b · MoQLE
A team of models on your device: qev-0.8b + a router + 2-bit LoRA experts (games, e2e). Mixture of Quantized LoRA Experts.
Note NVIDIA / CUDA: router + experts, fast engine
labqoat/squad-0.8b-MLX
0.8B • Updated • 37Note Apple silicon (MLX), bf16 and 8-bit
labqoat/squad-0.8b-GGUF
10.6M • Updated • 682Note llama.cpp: CPU, Metal, CUDA, Vulkan
labqoat/qev-0.8b
Image-Text-to-Text • 0.9B • Updated • 392 • 14Note The trunk, unchanged: squad-0.8b without experts