---
title: "GPU VRAM Calculator (Model Size & GPU Fit)"
method: POST
path: "/api/v1/tools/gpu-vram-calculator"
tags: ["ai"]
---

# GPU VRAM Calculator (Model Size & GPU Fit)

`POST /api/v1/tools/gpu-vram-calculator`

## Request

- Base URL: `https://calcfleet.com`
- URL: `https://calcfleet.com/api/v1/tools/gpu-vram-calculator`
- Auth: none declared

Calculate the VRAM a large language model needs by parameter count and precision (fp16, int8, int4), then see which GPU it fits — from RTX 4090 to H100.

## Request body

- object
  - `paramsBillion` number, required
  - `precision` 'fp32' | 'fp16' | 'bf16' | 'int8' | 'int4', required
  - `overheadPct` number, required

## Response `200`

Successful calculation result.

- object
  - `result` object, required: Structured calculation output (fields vary per calculator).

## Other responses

- `400`: Invalid input — the issues array contains Zod validation errors.
- `403`: Forbidden — an Authorization: Bearer cf_… key was supplied but is invalid.
- `404`: Unknown tool slug.

---

[API](https://skmtc.dev/calcfleet/apis/calcfleet-financial-calculators-api.md) · [All operations](https://skmtc.dev/calcfleet/apis/calcfleet-financial-calculators-api/llms.txt) · [OpenAPI document](https://skmtc.dev/calcfleet/apis/calcfleet-financial-calculators-api/revisions/cd9abd595bbe?raw)