Home / Developer / LLM VRAM Estimator

LLM VRAM Estimator

Estimate weight memory for a parameter count and data type. INT4 uses 0.5 bytes per parameter.

  1. 1Enter input
  2. 2Set options
  3. 3Get results

This calculator runs in your browser. Nothing is sent to a server.

Model size in billions of parameters.

Bytes per parameter for stored weights. INT4 is 4 bits = 0.5 bytes.

How it works

  1. Enter parameters in billions as a number.
  2. Choose a weight type. INT4 is 0.5 bytes per parameter.
  3. Process to see decimal GB and binary GiB.

No files. Settings may be shared; nothing is uploaded.

Weight storage only. KV cache and activations are omitted.

Supported inputs and outputs

No file formats. Numeric parameter count and weight type.

Example

8 billion INT4 parameters → 4.000 GB = 3.725 GiB.

Questions and answers

Does this include KV cache?

No. The estimate is weight storage only.