exllamav3 comfortably beats llama.cpp running CPU-offloaded Qwen-3.8-Flash-Next on my setup!

I got 2x 20GB RTX 3080s + 128GB of DDR4 2666hz RAM (only 4 of 6 channels populated) + a Xeon 6148 I've always been a llama.cpp person and I've been running Unsloth's Q4_K_XL quant of Qwen 3.8 Flash Next at ~270tps prefill and ~13tps decode (starts off close to 20 and falls down to 13 with growing c

中文全文翻译正在补齐，可先查看下方英文原文。

I got 2x 20GB RTX 3080s + 128GB of DDR4 2666hz RAM (only 4 of 6 channels populated) + a Xeon 6148 I've always been a llama.cpp person and I've been running Unsloth's Q4_K_XL quant of Qwen 3.8 Flash Next at ~270tps prefill and ~13tps decode (starts off close to 20 and falls down to 13 with growing c