Qualcomm launches GenieX to run LLMs on their Windows Laptops
英文标题：Qualcomm launches GenieX to run LLMs on their Windows Laptops
Qualcomm was behind every major chipmaker so they are playing catchup when it comes to SDKs. https://aihub.qualcomm.com/geniex I was able to get 20 tok/s running Gemma 4 26B A4B 0.5s for first token running on the GPU or NPU 10 tok/s on the GPU for Qwen 3.6 27B MTP To use llama.cpp, just get any Q4_
打开原文相关 3 · 机会 0
中文
Qualcomm was behind every major chipmaker so they are playing catchup when it comes to SDKs. https://aihub.qualcomm.com/geniex I was able to get 20 tok/s running Gemma 4 26B A4B 0.5s for first token running on the GPU or NPU 10 tok/s on the GPU for Qwen 3.6 27B MTP To use llama.cpp, just get any Q4_
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Qualcomm was behind every major chipmaker so they are playing catchup when it comes to SDKs. https://aihub.qualcomm.com/geniex I was able to get 20 tok/s running Gemma 4 26B A4B 0.5s for first token running on the GPU or NPU 10 tok/s on the GPU for Qwen 3.6 27B MTP To use llama.cpp, just get any Q4_