Nemotron 3.5 Lightning 30B (3B active)
on 2× Intel Arc Pro B60 24GB · llama.cpp
Oct 3, 2026
Use cases
agenticcoding
Summary
User reports Nemotron 3.5 Lightning 30B-A3B at 91.91 tok/s decode on 2x Intel Arc Pro B60 24GB.
Setup is llama.cpp SYCL with Q4_0 weights and an MTP Q8_0 drafter at --spec-draft-n-max 7, 22.18 GiB VRAM, 1,760 tok/s prefill at 12K context.
MTP acceptance is 99.5-100% at every n-max; the model needs the whole card with no co-residence.