---
title: "Analyze Model"
method: GET
path: "/guess/vllm_config"
tags: ["ConfigGuesser"]
---

# Analyze Model

`GET /guess/vllm_config`

Attempt to guess required GPU count and VRAM for a model on huggingface, assuming safetensors format.

## Query parameters

- `model` string, required

## Response `200`

Successful Response

- GPURequirements
  - `total_model_size` integer, required
  - `required_gpus` integer, required
  - `min_vram_per_gpu` integer, required
  - `model_type` string, required
  - `quantization` string, nullable, required
  - `num_attention_heads` integer, required
  - `num_key_value_heads` integer, nullable, required
  - `hidden_size` integer, required
  - `num_layers` integer, required

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/chutes/apis/fastapi.md) · [All operations](https://skmtc.net/chutes/apis/fastapi/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/chutes/fastapi/revisions/352418d4e3a2/schema)