99 <!-- SEO Meta Tags -->
1010 < meta name ="keywords " content ="LLM benchmark, AI model speed test, tokens per second, OpenAI GPT benchmark, Claude benchmark, Gemini benchmark, LLM performance, inference speed ">
1111 < meta name ="author " content ="pietz ">
12- < link rel ="canonical " href ="https://pietz.github.io/ tacho/ ">
12+ < link rel ="canonical " href ="https://tacho.sh / ">
1313
1414 <!-- Open Graph / Facebook -->
1515 < meta property ="og:type " content ="website ">
16- < meta property ="og:url " content ="https://pietz.github.io/ tacho/ ">
16+ < meta property ="og:url " content ="https://tacho.sh / ">
1717 < meta property ="og:title " content ="Tacho - LLM Speed Test ">
1818 < meta property ="og:description " content ="Benchmark LLM inference speed across multiple models and providers. Get tokens/second metrics to compare model performance. ">
19- < meta property ="og:image " content ="https://pietz.github.io/ tacho/og-image.png ">
19+ < meta property ="og:image " content ="https://tacho.sh /og-image.png ">
2020
2121 <!-- Twitter -->
2222 < meta property ="twitter:card " content ="summary_large_image ">
23- < meta property ="twitter:url " content ="https://pietz.github.io/ tacho/ ">
23+ < meta property ="twitter:url " content ="https://tacho.sh / ">
2424 < meta property ="twitter:title " content ="Tacho - LLM Speed Test ">
2525 < meta property ="twitter:description " content ="Benchmark LLM inference speed across multiple models and providers. Get tokens/second metrics to compare model performance. ">
26- < meta property ="twitter:image " content ="https://pietz.github.io/ tacho/og-image.png ">
26+ < meta property ="twitter:image " content ="https://tacho.sh /og-image.png ">
2727
2828 <!-- Favicon -->
2929 < link rel ="icon " href ="data:image/svg+xml,<svg xmlns=%22http://www.w3.org/2000/svg%22 viewBox=%220 0 100 100%22><text y=%22.9em%22 font-size=%2290%22>⚡</text></svg> ">
3737 "applicationCategory" : "DeveloperApplication" ,
3838 "operatingSystem" : "Windows, macOS, Linux" ,
3939 "description" : "Fast CLI tool for benchmarking LLM inference speed across multiple models and providers" ,
40- "url" : "https://pietz.github.io/ tacho/" ,
40+ "url" : "https://tacho.sh /" ,
4141 "author" : {
4242 "@type" : "Person" ,
4343 "name" : "pietz" ,
4949 "priceCurrency" : "USD"
5050 } ,
5151 "softwareVersion" : "Latest" ,
52- "screenshot" : "https://pietz.github.io/ tacho/screenshot.png"
52+ "screenshot" : "https://tacho.sh /screenshot.png"
5353 }
5454 </ script >
5555
373373
374374 < main >
375375 < section class ="hero animate-in ">
376- < h1 > Tacho - LLM Speed Test</ h1 >
377- < p class ="tagline "> Benchmark inference speed across models and providers </ p >
376+ < h1 > tacho - LLM Speed Test</ h1 >
377+ < p class ="tagline "> Measure and compare AI model inference time in the CLI </ p >
378378
379379 < div class ="terminal ">
380380 < div class ="terminal-header ">
@@ -397,7 +397,7 @@ <h1>Tacho - LLM Speed Test</h1>
397397
398398 < section class ="animate-in " style ="animation-delay: 0.1s; ">
399399 < h2 > Quick Start</ h2 >
400- < p > Get started in seconds with uv or pip :</ p >
400+ < p > Run tacho with "uv" without installation :</ p >
401401
402402 < div class ="code-block ">
403403 < code id ="installCmd "> uvx tacho gpt-4.1-nano gemini/gemini-2.0-flash</ code >
@@ -407,7 +407,7 @@ <h2>Quick Start</h2>
407407 < p > Or install globally:</ p >
408408
409409 < div class ="code-block ">
410- < code id ="pipCmd "> pip install tacho</ code >
410+ < code id ="pipCmd "> uv tool install tacho</ code >
411411 < button class ="copy-button " onclick ="copyToClipboard('pipCmd', this) "> Copy</ button >
412412 </ div >
413413 </ section >
0 commit comments