inference-optimization/GLM-5.2-0.8B-A0.8B Text Generation • 0.8B • Updated about 1 month ago • 3.15k • 3
Running on Zero Agents 6 Cosmos3-Super-Text2Image (NVFP4) 🌌 6 NVIDIA Cosmos3-Super 64B text-to-image, NVFP4 quantization