aidatatools/ollama-benchmark
LLM Benchmark for Throughput via Ollama (Local LLMs)
This tool helps you quickly understand the real performance of your local Large Language Models (LLMs) running via Ollama. It takes your existing local LLM setup and provides a clear tokens-per-second metric. AI/ML practitioners, researchers, or anyone experimenting with local LLMs can use this to assess different models and hardware configurations.
345 stars.
Use this if you need to measure the raw inference speed (throughput) of various LLMs on your local machine to compare performance or optimize your setup.
Not ideal if you are looking to benchmark the accuracy, quality, or specific application performance of an LLM, as this tool focuses solely on throughput.
Stars
345
Forks
41
Language
Python
License
MIT
Category
Last pushed
Jan 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/aidatatools/ollama-benchmark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related models
stanfordnlp/axbench
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
LarHope/ollama-benchmark
Ollama based Benchmark with detail I/O token per second. Python with Deepseek R1 example.
qcri/LLMeBench
Benchmarking Large Language Models
THUDM/LongBench
LongBench v2 and LongBench (ACL 25'&24')
microsoft/LLF-Bench
A benchmark for evaluating learning agents based on just language feedback