Qwen3.8-Flash-Next + MTP on Strix Halo: Vulkan Runtime Notes
英文标题：Qwen3.8-Flash-Next + MTP on Strix Halo: Vulkan Runtime Notes
Below are the benchmark results for running Qwen3.8-Flash-Next on Strix Halo using the Vulkan backend of llama.cpp, combined with MTP model. Hardware Item Details CPU AMD Ryzen AI MAX+ 395 (16C/32T) GPU Radeon 8060S (integrated, RADV STRIX_HALO) RAM 128GB unified memory Software Item De
打开原文相关 4 · 机会 2
中文
Below are the benchmark results for running Qwen3.8-Flash-Next on Strix Halo using the Vulkan backend of llama.cpp, combined with MTP model. Hardware Item Details CPU AMD Ryzen AI MAX+ 395 (16C/32T) GPU Radeon 8060S (integrated, RADV STRIX_HALO) RAM 128GB unified memory Software Item De
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Below are the benchmark results for running Qwen3.8-Flash-Next on Strix Halo using the Vulkan backend of llama.cpp, combined with MTP model. Hardware Item Details CPU AMD Ryzen AI MAX+ 395 (16C/32T) GPU Radeon 8060S (integrated, RADV STRIX_HALO) RAM 128GB unified memory Software Item De