WritingBasetenBasetenpublished Aug 7, 2025seen 2h

Sota Performance For Gpt Oss 120b On Nvidia Gpus

Open original ↗

Captured source

source ↗

No source text has been captured for this signal yet. The original source is linked below.

source ↗

Notability

TensorRT-LLM is fast but notoriously hard; title oversells single-GPU throughput.