DEDUPED Hot AI repos, turned into use cases Get the Monday 5
156 stars · TypeScript

How to use Llmspeed: what you can do with it

What is Llmspeed? llmspeed is a static web app that simulates how fast a local LLM streams tokens on a chosen GPU, Mac or CPU, so you can judge speed before buying hardware.

How do I use it? Open https://llmspeed.dev in a browser; then pick a GPU or Mac from the list and choose a model; check the memory fit result for each quantization: fits, needs partial offload to system RAM, or won't run. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Check local LLM speed before buying hardware

    Pick a GPU or Mac and model to see the streamed speed and whether it fits in memory.

    View prompt
    Using the llmspeed repo (github.com/nicorobinreal/llmspeed) at https://llmspeed.dev, check the simulated speed and memory fit for <model name> on <hardware name>. Expected output: tokens per second, time to first token, and fit status for each quantization. Verify that the trust label (Measured, Derived or Projected) is shown next to the speed figure.

  • Compare two machines side by side in race mode

    Run two setups against the same model and share the race link with others.

    View prompt
    Using the llmspeed repo (github.com/nicorobinreal/llmspeed) at https://llmspeed.dev, set up a race between <hardware A> and <hardware B> on <model name>. Expected output: a side-by-side streamed race and a shareable link. Verify that both sides use the same model before you share the link.

  • Submit a real llama-bench result as a pull request

    Run llama-bench on your machine and add a verified row to the benchmark CSV.

    View prompt
    In the llmspeed repo (github.com/nicorobinreal/llmspeed), run `llama-bench -m <model.gguf> -p 512 -n 128` and append one row to benchmarks/submissions.csv. Expected output: a pull request with one new CSV row and the full llama-bench output in the description. Verify that gen_tps matches the tg128 result and prefill_tps matches the pp512 result.

  • Run Llmspeed locally to test prediction data

    Install dependencies, start the dev server and build the static site from the repo.

    View prompt
    In the llmspeed repo (github.com/nicorobinreal/llmspeed), run `npm install`, then `npm run dev`, and report the local URL. Expected output: a running dev server and a successful `npm run build`. Verify that data/app-data.json loads in the app without errors.

Quick start with Llmspeed

  1. Check you have what it needs: A web browser to use llmspeed.dev; For contributing a benchmark: a machine with llama.cpp and a .gguf model file; For local development: npm.
  2. Open nicorobinreal/llmspeed on GitHub and read the README and license.
  3. Open https://llmspeed.dev in a browser.
  4. Pick a GPU or Mac from the list and choose a model.
  5. Check the memory fit result for each quantization: fits, needs partial offload to system RAM, or won't run.
  6. Watch the answer stream and note the wait before the first token for your typical prompt length.

These steps come from our top use case, Check local LLM speed before buying hardware, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for nicorobinreal/llmspeed

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Llmspeed alternatives · Best AI repos for Money

About this repo

Requirements

  • A web browser to use llmspeed.dev
  • For contributing a benchmark: a machine with llama.cpp and a .gguf model file
  • For local development: npm

Add this badge to your README

Maintain Llmspeed? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/nicorobinreal/llmspeed.svg)](https://dedupedai.com/use-cases/nicorobinreal-llmspeed/?utm_source=github&utm_medium=badge&utm_campaign=nicorobinreal-llmspeed)

HTML 

<a href="https://dedupedai.com/use-cases/nicorobinreal-llmspeed/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=nicorobinreal-llmspeed"><img src="https://dedupedai.com/badge/nicorobinreal/llmspeed.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Llmspeed

What is Llmspeed?

llmspeed is a static web app that simulates how fast a local LLM streams tokens on a chosen GPU, Mac or CPU, so you can judge speed before buying hardware. It is an open-source project on GitHub: https://github.com/nicorobinreal/llmspeed.

How do I use Llmspeed?

Open https://llmspeed.dev in a browser; then pick a GPU or Mac from the list and choose a model; check the memory fit result for each quantization: fits, needs partial offload to system RAM, or won't run. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Llmspeed for?

Someone deciding whether a GPU, Mac or CPU is fast enough for a local model before spending money on it.

What can I do with Llmspeed?

4 use cases so far, for example: Check local LLM speed before buying hardware; Compare two machines side by side in race mode; Submit a real llama-bench result as a pull request. Each has steps and a copy-paste agent prompt.

What do I need to run Llmspeed?

A web browser to use llmspeed.dev; For contributing a benchmark: a machine with llama.cpp and a .gguf model file; For local development: npm.

What are alternatives to Llmspeed?

Other hot AI repos in Money: Fincept Terminal, Freqtrade, Vibe Trading, Day Trader Skill, Tick Stock Panel.

Is Llmspeed safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.