What LLM Can I Run?
Detect your GPU with one click and see which LLMs your computer can actually run — Llama, Gemma, Qwen, DeepSeek and 5...
What What LLM Can I Run? does
What LLM Can I Run? is a developer tool that identifies which open-source Large Language Models a user's hardware can execute. By detecting GPU specifications with a single click, it compares the user's VRAM and processing power against a catalog of models like Llama, Gemma, Qwen, and DeepSeek, ranking results by whether they fit in available VRAM, require CPU offloading, or will not run. The output helps users understand their computational capabilities without manual benchmarking. The Inventive HQ version distinguishes itself by offering a streamlined, one-click GPU detection workflow that immediately surfaces model compatibility rankings. Unlike broader hardware analysis tools, it focuses specifically on LLM runnability, presenting results grouped by fit (VRAM fit, CPU offloading needed, won't run) rather than raw specifications. The interface avoids technical jargon where possible, translating detected hardware into actionable model recommendations directly relevant to developers exploring local AI deployment.
How to use the Inventive HQ What LLM Can I Run?
- 1
Click the detection button to identify your GPU specifications
- 2
Review the ranked list of compatible LLMs showing fit status (VRAM fit, CPU offloading, won't run)
- 3
Select a model from the results to see its specific requirements
- 4
Compare your hardware against model VRAM thresholds to understand limitations
- 5
Use the results to decide which open-source models are viable for local execution
Best for
Developers and AI enthusiasts with consumer-grade hardware who want to quickly determine which open-source LLMs they can run locally without purchasing additional infrastructure.
Limitations
- Results depend on accurate GPU detection; misidentified hardware may produce incorrect recommendations
- No unit switching or detailed specification customization beyond detected values
- Results are estimates based on typical model sizes and may not reflect exact performance on specific hardware configurations
What LLM Can I Run? FAQ
- Do I need a dedicated GPU to use this tool?
- No, the tool detects your available hardware including integrated graphics and will rank models based on what your system can support, though dedicated GPUs typically offer more options.
- Can I trust the model compatibility rankings?
- The rankings are based on standard VRAM requirements for each model, but actual performance may vary depending on your specific hardware configuration and optimization settings.
- What happens if my hardware doesn't meet minimum requirements?
- The tool will categorize those models as 'won't run' or 'requires CPU offloading,' indicating they may be too large for your VRAM or will run very slowly without specialized configuration.
- Are the listed models limited to specific license types?
- The catalog includes popular open-source models like Llama, Gemma, Qwen, and DeepSeek, but you should verify individual model licenses before commercial use as restrictions may apply.