rohanelukurthy/rig-rank
A Go CLI tool to benchmark local LLMs via Ollama, measuring Time To First Token (TTFT) and throughput on your specific hardware.
This tool helps you understand how well Large Language Models (LLMs) run on your personal computer. It takes a local LLM (like Llama 3) and measures how fast it starts generating text and how quickly it produces words. This is for anyone setting up local AI models who wants to know if their computer can handle the workload and which models will perform best.
Use this if you are running LLMs locally via Ollama and need to benchmark their speed and responsiveness on your specific hardware.
Not ideal if you need to evaluate the accuracy, intelligence, or factual correctness of an LLM's responses, as it focuses purely on speed metrics.
Stars
18
Forks
2
Language
Go
License
MIT
Category
Last pushed
Feb 24, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/rohanelukurthy/rig-rank"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
sierra-research/tau2-bench
τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
xlang-ai/OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
bigcode-project/bigcodebench
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
THUDM/AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
scicode-bench/SciCode
A benchmark that challenges language models to code solutions for scientific problems