boltbeam.fyi

L40S for local LLMs

4 measured runs. 45 GB of VRAM; memory measured at 762 GB/s, which sets the roofline for every model below.

ModelQuantEnginetok/sRooflineShare
Qwen3-14BAWQvLLM77.789.487%
Qwen3-14BQ4_K_Mllama.cpp74.188.184%
Qwen3.8-27BW4A16-AWQvLLM43.648.989%
Qwen3.8-27BUD-Q4_K_Mllama.cpp40.048.483%

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 →