Qwen3.8 27B
on 4× NVIDIA V100 16GB · v100-skinny
Summary
User reports Qwen3.8 NVFP4 on four Tesla V100s (2017) via a custom v100-skinny engine matching RTX 5090 decode throughput at ~220 tok/s.
Setup uses QPN kernels to translate FP4/FP8 to FP16 for Volta tensor cores.
Long-context tests show MTP depth k=3 better at ~65K context. The figure is for 4 GPUs versus 1, is not power efficient, and prefill is slower.