Llm Requirements Calculator API

POST https://api.findutils.com/api/tools/llm-requirements-calculator/execute

Estimate the VRAM, system RAM, and disk space needed to run an open-weight LLM locally, and which common GPUs and Macs it fits on. Covers Llama, Mistral, Qwen, DeepSeek, Gemma, Phi, Code Llama, Command R, Yi, SmolLM, StableLM, Grok, Falcon, and MiniCPM across FP32 through Q2_K quantization.

Open the tool Try it

Request body

application/json

model

string required

Model id (or exact display name). One of: llama-3.2-1b, llama-3.2-3b, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, mistral-7b, mistral-nemo, mixtral-8x7b, mixtral-8x22b, mistral-small-3, qwen-2.5-0.5b, qwen-2.5-1.5b, qwen-2.5-3b, qwen-2.5-7b, qwen-2.5-14b, qwen-2.5-32b, qwen-2.5-72b, qwen-2.5-coder-7b, qwen-2.5-coder-32b, qwen-qwq-32b, deepseek-r1-distill-7b, deepseek-r1-distill-14b, deepseek-r1-distill-32b, deepseek-r1-distill-70b, deepseek-v3, deepseek-r1, gemma-2-2b, gemma-2-9b, gemma-2-27b, phi-3-mini, phi-3-medium, phi-4, codellama-7b, codellama-13b, codellama-34b, codellama-70b, qwen-3-0.6b, qwen-3-1.7b, qwen-3-4b, qwen-3-8b, qwen-3-14b, qwen-3-32b, qwen-3-235b, command-r-35b, command-r-plus, yi-1.5-6b, yi-1.5-9b, yi-1.5-34b, smollm-2-135m, smollm-2-360m, smollm-2-1.7b, stablelm-2-1.6b, stablelm-2-12b, grok-1, falcon-3-1b, falcon-3-3b, falcon-3-7b, falcon-3-10b, minicpm-3-4b. One of llama-3.2-1b · llama-3.2-3b · llama-3.1-8b · llama-3.1-70b · llama-3.1-405b · mistral-7b · mistral-nemo · mixtral-8x7b · mixtral-8x22b · mistral-small-3 · qwen-2.5-0.5b · qwen-2.5-1.5b · qwen-2.5-3b · qwen-2.5-7b · qwen-2.5-14b · qwen-2.5-32b · qwen-2.5-72b · qwen-2.5-coder-7b · qwen-2.5-coder-32b · qwen-qwq-32b · deepseek-r1-distill-7b · deepseek-r1-distill-14b · deepseek-r1-distill-32b · deepseek-r1-distill-70b · deepseek-v3 · deepseek-r1 · gemma-2-2b · gemma-2-9b · gemma-2-27b · phi-3-mini · phi-3-medium · phi-4 · codellama-7b · codellama-13b · codellama-34b · codellama-70b · qwen-3-0.6b · qwen-3-1.7b · qwen-3-4b · qwen-3-8b · qwen-3-14b · qwen-3-32b · qwen-3-235b · command-r-35b · command-r-plus · yi-1.5-6b · yi-1.5-9b · yi-1.5-34b · smollm-2-135m · smollm-2-360m · smollm-2-1.7b · stablelm-2-1.6b · stablelm-2-12b · grok-1 · falcon-3-1b · falcon-3-3b · falcon-3-7b · falcon-3-10b · minicpm-3-4b.
quantization

string optional

Quantization id. Default: "q4_k_m". One of fp32 · fp16 · q8_0 · q6_k · q5_k_m · q4_k_m · q3_k_m · q2_k. Default "q4_k_m".
context_length

integer optional

Context window in tokens (512-131072). Default: 8192. Default 8192.
batch_size

integer optional

Concurrent sequences (1-64). Default: 1. Default 1.

Example arguments

Verified

{
  "model": "llama-3.1-8b",
  "quantization": "q4_k_m",
  "context_length": 8192
}

curl -X POST https://api.findutils.com/api/tools/llm-requirements-calculator/execute \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.1-8b",
    "quantization": "q4_k_m",
    "context_length": 8192
  }'

const response = await fetch('https://api.findutils.com/api/tools/llm-requirements-calculator/execute', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({"model":"llama-3.1-8b","quantization":"q4_k_m","context_length":8192}),
});
const data = await response.json();

import requests

response = requests.post(
    "https://api.findutils.com/api/tools/llm-requirements-calculator/execute",
    json={"model":"llama-3.1-8b","quantization":"q4_k_m","context_length":8192},
)
data = response.json()

$ch = curl_init('https://api.findutils.com/api/tools/llm-requirements-calculator/execute');
curl_setopt_array($ch, [
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => ['Content-Type: application/json'],
    CURLOPT_POSTFIELDS => '{"model":"llama-3.1-8b","quantization":"q4_k_m","context_length":8192}',
    CURLOPT_RETURNTRANSFER => true,
]);
$data = json_decode(curl_exec($ch), true);

Also an MCP tool

Call llm_requirements_calculator from Claude, Cursor or any MCP client. Same arguments, same output.

https://mcp.findutils.com

MCP reference

Rate limit: 60 a minute, per IP
Auth: None
REST id: llm-requirements-calculator
MCP name: llm_requirements_calculator
Category: Calculators
Machine-readable: openapi.json · markdown.md

Request body

Example arguments

More Calculators tools

More to explore