SGLang on the NVIDIA RTX 5090
llamaperf has 6 SGLang reports on the NVIDIA RTX 5090, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.
6 SGLang reports on the NVIDIA RTX 5090
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3.8 27B · NVFP4139.7 t/s(speculative decoding)
- Qwen3.8 27B · NVFP4152.0 t/s(speculative decoding)
- Qwen3.8 27B · NVFP4100.0 t/s(speculative decoding)
- Qwen3.8 27B · NVFP4200.0 t/s
- Qwen3.8 27B · W282.6 t/s
- Qwen3.8 27B · NVFP4144.0 t/s(speculative decoding)
Frequently asked
How fast is SGLang on the NVIDIA RTX 5090?
llamaperf has 6 SGLang reports on the NVIDIA RTX 5090, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.