Hello My GPU is A6000 Ada 48GB VRAM and it cannot support FP8 or AWQ-8bit varent. so I ask you to release FP6. Its accuracy is better than AWQ-4bit . I mean this model: https://huggingface.co/moonshotai/Kimi-Linear-48B-A3B-Instruct Thank you.
Hello
My GPU is A6000 Ada 48GB VRAM and it cannot support FP8 or AWQ-8bit varent. so I ask you to release FP6. Its accuracy is better than AWQ-4bit .
I mean this model: https://huggingface.co/moonshotai/Kimi-Linear-48B-A3B-Instruct
Thank you.