ExLlamaV3 on the NVIDIA RTX 5090
llamaperf has 3 ExLlamaV3 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.
3 ExLlamaV3 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.
- GLM-5.3 320B · 18B active · 2.05bpw EXL364.8 t/s(2 cards, speculative decoding, part in system RAM)
- Qwen3.8 125B · 6B active · 2.50bpw241.7 t/s(2 cards, speculative decoding)
- Qwen3.8 125B · 6B active · 2.50bpw EXL3291.1 t/s(2 cards, speculative decoding)
Frequently asked
How fast is ExLlamaV3 on the NVIDIA RTX 5090?
llamaperf has 3 ExLlamaV3 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.