Can YOUR computer run THIS Large Language Model?

Enter Model Configuration

It's okay if you don't have all the details about the model. Only the number of parameters and the quantization level are essential. For a more precise calculation, refer to the config.json file on the model's Hugging Face page. Switch from simple to advanced mode for a more detailed estimation.

Calculation Mode
Predefined Model
Model Parameters
Quantization Level
Context Window
KV Cache Quantization
Number of Attention Heads
Number of Key-Value Heads
Hidden Size
Number of Hidden Layers

Enter Model Configuration

Enter your GPU VRAM and RAM details to determine which models are compatible with your system. Enter your GPUs and RAMs bandwidth to calculate the tokens per second.


Operating System:

System RAM (GB)
RAM Bandwidth (GB/s)
GPU VRAM (GB)
GPU Bandwidth (GB/s)

Click on the button below to see which models your system can run.



Results