QVAC Logo

getModelInfo( )

Retrieves detailed information about a model, including cache status and loaded instances.

function getModelInfo(params): Promise<ModelInfo>;

Parameters

NameTypeRequired?Description
paramsobjectThe query parameters
params.namestringThe model name to look up

Returns

Promise<ModelInfo> — Detailed information about the model.

ModelInfo

FieldTypeDescription
namestringModel name
modelIdstringUnique model identifier
addon"llm" | "whisper" | "embeddings" | "nmt" | "vad" | "tts" | "ocr" | "other"Model addon type
expectedSizenumberExpected total file size in bytes
sha256ChecksumstringSHA-256 checksum
isCachedbooleanWhether the model is fully cached locally
isLoadedbooleanWhether the model is currently loaded in memory
cacheFilesCacheFileInfo[]Individual cache file details
registryPathstringRegistry path (optional)
registrySourcestringRegistry source (optional)
enginestringInference engine (optional)
quantizationstringQuantization level (optional)
paramsstringModel parameter count (optional)
actualSizenumberActual cached size in bytes (optional)
cachedAtDateWhen the model was cached (optional)
loadedInstancesLoadedInstance[]Currently loaded instances (optional)

CacheFileInfo

FieldTypeDescription
filenamestringFile name
pathstringFull file path
expectedSizenumberExpected size in bytes
sha256ChecksumstringSHA-256 checksum
isCachedbooleanWhether this file is cached
actualSizenumberActual file size (optional)
cachedAtDateWhen this file was cached (optional)

LoadedInstance

FieldTypeDescription
registryIdstringRegistry identifier for this loaded instance
loadedAtDateWhen the model was loaded
configunknownModel configuration used at load time (optional)

Throws

ErrorWhen
INVALID_RESPONSE_TYPEResponse type does not match expected "getModelInfo"

Example

import { getModelInfo } from "@qvac/sdk";

const info = await getModelInfo({ name: "Llama 3.2 3B Q4" });
console.log(`Cached: ${info.isCached}, Loaded: ${info.isLoaded}`);
console.log(`Size: ${info.expectedSize} bytes`);

On this page