Your browser does not seem to support JavaScript. As a result, your viewing experience will be diminished, and you have been placed in read-only mode.
Please download a browser that supports JavaScript, or enable it if it's disabled (i.e. NoScript).
壕无人性哈哈哈哈
向优秀老哥学习选配了rtx pro 5000 48GB + 64GB RAM，目前用llama.cpp 跑qwen3.8 27b Q8 KV 256k 个人用单并发，但是感觉任务一长速度上不去大概decode 30T左右，prefill也是2000多。老哥decode 130t/s，prefill2600 t/s，这个速度非常不错了感觉，不知道flash模型使用质量体感比27b怎么样？
游