RunThisLLM
FreeSee which LLMs you can run on your hardware.
FreeFree tier
About RunThisLLM
RunThisLLM is a comprehensive hardware requirements database for local AI models, featuring over 295 models including Llama, Qwen, DeepSeek, Mistral, Gemma, Phi, FLUX, Whisper, and more. Users can search by model to get full build specs, VRAM requirements, performance estimates, and benchmark scores, or search by hardware to see which models can run on their system. The tool also offers a Chrome extension for quick lookups and a custom machine building service for users who want a system optimized for their specific models.
Key Features
Searchable database of 295+ local AI models (Llama, Qwen, DeepSeek, Mistral, Gemma, Phi, FLUX, Whisper, and more)
Two search modes: ‘I have hardware – what can I run?’ and ‘I have a model – what do I need?’
VRAM requirements, full build specs, performance estimates, and benchmark scores for each model
Categories spanning General chat, Code generation, Reasoning, Vision, Image generation, Video generation, Audio, Embeddings, Medical, Finance, Legal, and 3D generation
Custom PC build service: submit your models and use case to get a tailor-made machine shipped
Free Chrome extension for side-panel lookups without tab switching
Pros & Cons
Pros
- Free to use with no account required
- Covers a wide range of model types and categories beyond just text LLMs
- Provides concrete VRAM numbers and benchmark data for informed hardware decisions
- Chrome extension makes it convenient to check requirements while browsing
- Custom build service saves users from specing out hardware themselves
Cons
- Database is limited to listed 295+ models; less common models may not be present
- Requires JavaScript enabled in the browser to function
- No cloud GPU pricing or hosted inference comparisons provided
- Custom machine building service likely involves additional cost (not disclosed on site)
Best For
Determining whether a local AI model can run on existing hardwarePlanning a new PC build optimized for specific local LLMs or image/video generation modelsComparing VRAM and performance requirements across different modelsSelecting the right hardware for research, software development, creative projects, or hobbyist AI experimentation
FAQ
What models are currently in the database?
RunThisLLM includes over 295 models such as Llama, Qwen, DeepSeek, Mistral, Gemma, Phi, FLUX, Whisper, and more across categories like General chat, Code generation, Reasoning, Vision, Image generation, Video generation, Audio, Embeddings, Medical, Finance, Legal, and 3D generation.
How does the hardware lookup work?
You can search in two ways: 'I have hardware' to see which models can run on your system, or 'I have a model' to get the full build specs, VRAM needs, performance estimates, and benchmark scores required to run that model locally.
Is there a Chrome extension?
Yes, a free Chrome extension is available that lets you look up hardware requirements for any model directly from your browser sidebar without switching tabs.
Can you build me a custom PC for running these models?
Yes, RunThisLLM offers a service where you submit the models you want to run along with your budget and use case, and they will spec, build, and ship a custom machine optimized for those models.