Run Benchmark - TokenMark WebGPU LLM Speed Test

Benchmark your device's local AI inference speed. Run Llama 3, Qwen, and other LLMs directly in your browser using WebGPU. Get your decode speed, prefill rate, and overall score.

Snapshot 2026-09-29 · 207 configs · 94 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.