boltbeam.fyi

H200 NVL for local LLMs

2 measured runs. 140 GB of VRAM; memory measured at 4513 GB/s, which sets the roofline for every model below.

ModelQuantEnginetok/sRooflineShare
Qwen3-14BQ4_K_Mllama.cpp135.0521.826%
Qwen3.8-27BUD-Q4_K_Mllama.cpp78.6286.727%

Share = measured tok/s over the roofline: the bytes a token reads over this GPU's measured memory speed. Open a quant for the test machine and the per-role and per-kernel breakdown.

Open the explorer on this GPU →