datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
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.gentoo-small-model-throughput-vllm
Small-model throughput + quality benchmarks (RTX 5060 Ti 16 GB)
Local vLLM throughput/scaling measurements and lighteval accuracy benchmarks for
sub-2B chat models on a 3× RTX 5060 Ti (16 GB) host. Raw JSON outputs plus comparison tables.
Setup
Setting
Value
Host
RTX 5060 Ti 16 GB (CUDA device 2)
GPU
CUDA device 2
Engine
vLLM 0.24
max_model_len
4096
gpu_memory_utilization
0.75
max_num_seqs
128
Gen length
128 tokens
Warmup / repeats
2 / 2… See the full description on the dataset page: https://huggingface.co/datasets/LostGentoo/gentoo-small-model-throughput-vllm.open-source-throughput-detailed
Open Sourced Data
more info coming soon!
open-source-throughput
Conversations Dataset
More info coming soon!
stability-throughput-classification-v0.1
What this dataset does
This dataset tests whether a model can detect healthy stability throughput.
The task is simple:
Given a scenario and a stability-throughput claim, predict whether the claim is supported.
Core stability idea
Throughput alone is not a success metric.
Stability throughput measures how much output a system can sustain while preserving critical properties.
A system shows healthy stability throughput when it can process increasing load without degrading:… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/stability-throughput-classification-v0.1.merged_qwen_throughput_evalafrica-synth-trade-port-throughput-performance-all
African Port Throughput Performance | Africa (Electric Sheep Africa metadata inventory)
Size category: 10K<n<100K - Formats: csv - Sector: infrastructure_transport - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Public… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-synth-trade-port-throughput-performance-all.merged_deepseek_throughput_eval5g-throughput-diagnosis-chatrtx-5080-llm-throughput
RTX 5080 Local LLM Throughput — Measured, Not Estimated
Measured decode and prefill tokens/second, load times, and VRAM residency for
local LLMs on a single retail NVIDIA GeForce RTX 5080 (16 GB): gpt-oss:20b
(MXFP4), Qwen 2.5 14B and 7B (Q4_K_M), and Llama 3.2 3B (Q4_K_M), at 4k and
16k context with ~500 and ~1,650-token prompts.
Method
Every figure is the median of 3 runs using ollama's native
eval_count/eval_duration counters — never wall-clock division.
Every… See the full description on the dataset page: https://huggingface.co/datasets/iBlessi/rtx-5080-llm-throughput.port_logistics_throughput.csv
Industrial & Logistics AI Research Dataset Collection (2024 Edition)
Overview
This repository provides a structured collection of industrial and logistics datasets
designed for artificial intelligence training, operational simulation,
and supply chain optimization research.
The datasets represent realistic industrial environments including
manufacturing production lines, warehouse inventory systems,
fleet management operations, predictive maintenance logs,
smart factory… See the full description on the dataset page: https://huggingface.co/datasets/Fdddhhhill/port_logistics_throughput.csv.tsa-throughput-2025throughput_batchthroughput_testpecan_throughput