Compute:Arena
Community submitted local AI benchmarks. 783 community benchmarks across 47 models and 17 chips, from 8 contributors. Decode and prefill tok/s by model, quantisation and chip, measured with BaseRT or llama.cpp. Benchmarking AI models on real hardware is way harder than it looks.
Reactions (1)
Similar products
by description similarity
A tool to benchmark LLM APIs (OpenAI
llmapitest.comClaude, local/self-hosted)
LocalScore
localscore.aiLocal LLM Benchmark
Local AI
github.comCurated resources for running LLMs on consumer hardware
This project collects GPU benchmarks from various cloud providers and compares them to fixed per token costs. Use our tool for efficient LLM GPU selections and cost-effective AI models. LLM provider price comparison, gpu benchmarks to price per token calculation, gpu benchmark table
ML-Dev-Bench
github.comBenchmarking AI Agents on Real-World AI Workflows