GitHub hosts HunyuanVideo, Tencent's open-source framework for large-scale video generation models, enabling AI-driven video creation.
What’s my local AI?
FreeStarting price
0Popularity
About What’s my local AI?
What’s my local AI? evaluates which local AI models can be run on a given machine by analyzing hardware specifications. The tool auto-detects GPU, RAM, VRAM, CPU cores, operating system, and WebGPU support from the browser, allowing users to manually adjust these values for hypothetical scenarios. It then lists compatible models, including options from LM Studio and Ollama, and indicates whether a model fits tightly or comfortably within the detected or adjusted hardware limits. The interface provides sorting and filtering options to refine model selection based on performance or size. The tool is designed for users interested in running AI models locally without relying on cloud services.
Key features
- Hardware auto-detection
- Manual hardware specification adjustment
- Model compatibility filtering
- Sorting by size or performance
- Support for LM Studio and Ollama models
- WebGPU and CPU compatibility checks
- Real-time model fit assessment
Use cases
- Checking local AI model compatibility before installation
- Comparing hardware requirements across different models
- Evaluating hypothetical hardware upgrades for AI workloads
Pros
- Auto-detects hardware specifications from the browser
- Allows manual adjustment of RAM, VRAM, CPU cores, and other parameters
- Provides compatibility checks for multiple local AI model frameworks
- No rate limits or usage quotas
- Supports offline and private model execution
Cons
- Requires waitlist signup to access
- Limited to models listed on the platform
- Hardware detection may not cover all edge cases
Frequently asked questions about What’s my local AI?
What does What's my local AI? do?
It evaluates which local AI models can run on a user's machine by analyzing hardware specifications such as GPU, RAM, VRAM, CPU cores, operating system, and WebGPU support. The tool provides a list of compatible models and indicates whether they fit tightly or comfortably within the detected or adjusted hardware limits.
Who is this tool designed for?
It is designed for users interested in running AI models locally without relying on cloud services, including developers, researchers, and privacy-conscious individuals who want to experiment with open-weight models on their own hardware.
How does the hardware detection work?
The tool auto-detects hardware specifications directly in the user's browser, including GPU, RAM, VRAM, CPU cores, operating system, and WebGPU support. Users can manually adjust these values to simulate different hardware configurations.
Can I use this tool without an internet connection?
Yes, the detection runs entirely locally in the browser, so no data is uploaded or shared. The tool functions offline after the initial page load.
What models are included in the compatibility list?
The tool lists compatible models from sources like LM Studio and Ollama, and provides options to filter and sort models based on performance or size.
How do I get started with What's my local AI?
Visit the website, allow JavaScript to run, and the tool will automatically detect your hardware specifications. Adjust values as needed and explore the list of compatible models to find the best fit for your system.
