Determine GPU requirements for large language models
Calculate GPU requirements for running LLMs
Merge Lora adapters with a base model
Convert PaddleOCR models to ONNX format
Display and filter leaderboard models
Retrain models for new data at edge devices
Persian Text Embedding Benchmark
Quantize a model for faster inference
Display leaderboard for earthquake intent classification models
Demo of the new, massively multilingual leaderboard
Evaluate open LLMs in the languages of LATAM and Spain.
Measure over-refusal in LLMs using OR-Bench
View LLM Performance Leaderboard
Can You Run It? LLM version is a specialized tool designed to help users determine the GPU requirements for running large language models (LLMs). It provides detailed insights into whether your hardware can support specific AI models, ensuring optimal performance and compatibility.
• GPU Compatibility Check: Quickly determine if your GPU can run popular LLMs.
• Performance Prediction: Estimate inference speed and memory usage for different models.
• Customizable Settings: Adjust parameters like batch size and sequence length to match your workflow.
• Benchmarking: Compare your GPU's performance against others in similar setups.
• Model Compatibility: Check support for the latest LLMs, including those from major frameworks.
• AI-Powered Recommendations: Get suggestions for upgrading or optimizing your hardware.
What GPUs are supported by Can You Run It? LLM version?
The tool supports a wide range of NVIDIA and AMD GPUs, with regular updates to include the latest models.
Is the performance prediction accurate?
The predictions are based on extensive benchmarks and real-world data, ensuring high accuracy for typical use cases.
Can I use this tool for models outside the supported list?
While the tool is optimized for popular LLMs, you can input custom model specifications for compatibility checks. Results may vary.