@altronis/tokenmark-cli

Recommend the best local-LLM model + config for your hardware, from real community benchmarks — TokenMark in your terminal.

It pulls the live benchmark snapshot from tokenmark.app and ranks measured configs (Strix Halo, DGX Spark, RTX, Mac). It never invents numbers — every pick is a real config with a source link.

Use

npx @altronis/tokenmark-cli recommend --hardware "Strix Halo" --tasks coding,reasoning --prefer balanced

Or install it:

npm i -g @altronis/tokenmark-cli
tokenmark recommend --hardware "DGX Spark" --tasks vision --prefer quality

Commands

tokenmark recommend --hardware <hw> [--tasks a,b] [--prefer speed|quality|balanced] [--limit N]
tokenmark configs   [--model <name>] [--hardware <hw>]
tokenmark search    <term>
tokenmark models

• --tasks: any of coding, reasoning, long-context, vision, agentic, general
• --prefer: speed (fastest), quality (most capable), balanced (default)

Point it at a different source with TOKENMARK_URL (default https://tokenmark.app).

What it shows

Each pick is a real measured config: decode tok/s, quant, backend, the hardware it ran on, why it was picked, who benchmarked it, and a link to the source. Aggregate/multi-GPU numbers are labeled so they aren't read as single-stream speed.

MIT licensed. Data aggregated from public community benchmarks with attribution.