vLLM on the Intel Arc Pro B70
llamaperf has 3 vLLM reports on the Intel Arc Pro B70, 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 vLLM reports on the Intel Arc Pro B70
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 125B · 6B active · W4A16-AutoRound70.0 t/s(4 cards, 2 requests at once)
- Qwen3.8 27B · EXL3 4.00bpw91.2 t/s(speculative decoding)
- Qwen3.8 27B · INT452.2 t/s(speculative decoding)
Frequently asked
How fast is vLLM on the Intel Arc Pro B70?
llamaperf has 3 vLLM reports on the Intel Arc Pro B70, 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.