Qwen3 30B (3B active)
on NVIDIA RTX 5090 · llama.cpp
Oct 8, 2026
Summary
User benchmarks Qwen3 MoE 30B-A3B at 352.06 t/s on an RTX 5090.
Setup is llama.cpp with Q4_K_M and flash attention, 99 layers offloaded to GPU.
This is the optimized run with kernel fusion and concurrent CUDA streams enabled; baseline was 246.96 t/s. The post also reports gpt-oss 20B MXFP4 at 419.14 t/s on the 5090 and both models on an RTX 4090.