throughput
llm-throughput-resultstsa-throughput-streaming-test4tsa-throughput-streaming-test2tsa-throughput-streaming-testtsa-throughput-streaming-test3quant_eval_throughput_telemetry
quant_eval — Throughput telemetry
One record per generation call across all published runs, pooled into a single union schema. Carries token counts, timing, and the token-count source per call.
Part of the quant_eval public corpus: a per-case behavioral evaluation of full-weight and quantized large language models across eight agent-relevant task families, with paired statistical testing.
Cite this dataset: 10.5281/zenodo.22009987 — concept DOI, always resolves to the latest… See the full description on the dataset page: https://huggingface.co/datasets/pbhappliedsystems/quant_eval_throughput_telemetry.
