vLLM 0.32.0
NVIDIA B300 x1 · tp1 × pp1- Speed per user (c=1)
- 41.2tok/s
- Time to first token
- 188ms
- Peak throughput
- 1,618tok/s @ 128
- Per GPU at peak
- 1,618tok/s
- Cold start
- 476s
- Context tested
- 8,192tokens
Measured 10 Nov 2026 · Throughput sweep
Measured 10 Nov 2026 · Throughput sweep
Measured 10 Nov 2026 · Throughput sweep
ModelPerf Pro