最終更新:2025-05-18 (日) 05:33:38 (58d)
Llama 3.1 8B
Top / Llama 3.1 8B
4bit量子化
- Q4_K_M
Ryzen AI Max+ 395 (EVO-X2) 36tok/s Apple M1 Ultra 63tok/s Apple M1 Max 47tok/s Snapdragon X Plus 19tok/s GeForce RTX 4060 Ti 44.64tok/s DGX Spark? ? Snapdragon 8 Elite 7.37tok/s Dimensity 9400 3.98tok/s - GPTQ 4bit
Jetson Orin Nano Super 19.14tok/s Jetson Orin Nano 14tok/s
