llmrun

What is llmrun?

llmrun is a website that answers the question of whether you can run a given open-weight language model on your own hardware. It detects your GPU or Mac in the browser, with nothing uploaded, or lets you pick a card or device yourself, then lists the models that fit along with an estimated VRAM need at Q4 quantization and expected tokens per second. Open models are ranked by a composite score and can be filtered by memory tier, from 8 GB up to 48 GB and beyond. A separate cloud section pulls hourly GPU prices from Vast.ai and RunPod, shows the cheapest card that fits each model size, and estimates cost per million output tokens. People use it before buying a GPU, choosing a Mac, or deciding between local inference and renting a card by the hour. The site publishes no subscription plans or prices for itself, so listing pricing is unknown, and its speed figures are estimates rather than measurements.

Use cases

• Check which LLMs fit my GPU
• Estimate VRAM needed for a model
• Compare tokens per second across devices
• Find the cheapest cloud GPU for a model
• Plan a GPU or Mac purchase for local AI
• Browse open models by memory tier

Who it's for

• Local AI hobbyists
• Developers
• ML engineers
• GPU buyers

Why use llmrun

• Browser-side detection shows what fits your hardware without installing anything or uploading data.
• Per-model VRAM and speed estimates help you avoid downloading a model that will not run.
• VRAM tiers make it easy to see what a 12 GB, 24 GB or 48 GB card can handle before you buy.
• Hourly cloud prices and per-token cost estimates help you decide between buying hardware and renting.
• Rankings by composite score give a quick shortlist of open models worth trying.

llmrun features

• In-browser detection of your GPU or Mac with no upload
• Manual selection from popular GPUs, MacBooks and AI boxes
• VRAM estimate at Q4 quantization for each model
• Estimated tokens per second per device
• Open model rankings by a composite score
• Browse models by VRAM tier from 8 GB to 48 GB
• Live cloud GPU prices from Vast.ai and RunPod, updated hourly
• Cheapest GPU that fits each model size, with cost per 1M output tokens
• Deploy links from cloud pricing pages

llmrun integrations

• Vast.ai
• RunPod

How to get started with llmrun

1. Open the site and let it detect your GPU or Mac in the browser, or choose a device from the list.
2. Review the models that fit, with VRAM at Q4, expected tokens per second and context length.
3. Filter the rankings by memory tier such as 12 GB, 24 GB or 48 GB.
4. Open the cloud page to compare hourly GPU rental prices and cost per million output tokens.
5. Use the deploy link for the card that suits the model you picked.

llmrun limitations

• Speeds and VRAM needs are estimates, not measurements on your own machine
• Cloud cost figures assume one user at a time on the cheapest card that fits
• It covers open models for local or rented GPUs, not hosted APIs

llmrun pricing

We couldn't confirm pricing on the official site. Check llmrun.dev for current prices.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

llmrun alternatives

The main llmrun alternatives listed on Debuly are LM Studio, Ollama, Hugging Face, Vast.ai, Runpod and Mydentify AI Model Cost Calculator. The table compares pricing and platforms; order is A–Z.

1. 

   Hugging Face

   Hub for hosting machine learning models, datasets and demo Spaces, with pay-as-you-go inference, GPU hardware and team plans.

   Developer platformsCodingResearch and search
   FreemiumVisit Hugging Face (official site)
2. 

   LM Studio

   Desktop app for running open language models on your own computer, now with the Bionic agent, a local API and optional US-hosted cloud models.

   Chat assistantsDeveloper platformsCodingProductivity
   FreemiumVisit LM Studio (official site)
3. 

   Mydentify AI Model Cost Calculator

   Free web calculator that compares monthly API costs of AI models from your request volume, token sizes and prompt caching.

   Developer platformsResearch and search
   FreeVisit Mydentify AI Model Cost Calculator (official site)
4. 

   Ollama

   Open-source app and CLI for running open AI models locally on macOS, Windows and Linux, with optional paid cloud models.

   Developer platformsCodingChat assistants
   Open sourceVisit Ollama (official site)
5. 

   Runpod

   Pay-per-second GPU cloud for AI: on-demand Pods, Serverless endpoints, multi-node Clusters and ready-made public model APIs.

   Developer platformsCoding
   PaidVisit Runpod (official site)
6. 

   Vast.ai

   GPU cloud marketplace for renting on-demand, interruptible or reserved GPUs with per-second billing.

   Developer platformsAutomation and agents
   PaidVisit Vast.ai (official site)

llmrun FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from llmrun.dev · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.