cd /news/large-language-models/nobodywho-is-an-inference-engine-tha… Β· home β€Ί topics β€Ί large-language-models β€Ί article
[ARTICLE Β· art-137943] src=github.com β†— pub= topic=large-language-models verified=true sentiment=↑ positive

NobodyWho is an inference engine that lets you run LLMs locally and efficiently

NobodyWho released an open-source inference engine that runs large language models locally and offline, built on llama.cpp and distributed as version 2.0.0 across Kotlin, Swift, Python, Flutter, React Native/Expo and Godot. The engine supports any GGUF-format model including Gemma, Qwen and Mistral, adds multimodal image and audio input, Whisper speech-to-text, Kokoro, Pocket TTS and Supertonic text-to-speech, and GPU acceleration via Vulkan or Metal. NobodyWho said the tool requires no API keys or hidden fees and generates structured grammars automatically from function signatures for type-safe tool calling.

read4 min views1 publishedSep 23, 2026
NobodyWho is an inference engine that lets you run LLMs locally and efficiently
Image: Michielbdejong (auto-discovered)

On-device AI for any device.

NobodyWho is an inference engine that lets you run LLMs locally and efficiently.

  • Run locally, offline β€” no API keys needed or hidden fees

  • Run any chat LLM β€” Gemma, Qwen, Mistral and more

  • Fast, type-safe tool calling β€” automatically generates structured grammars from your function signatures, no schema writing needed

  • Multimodal input β€” provide image and audio information to your LLM

  • Text-to-speech β€” synthesize local WAV audio with Kokoro, Pocket TTS and Supertonic backends

  • Speech-to-text β€” Transcribe audio into text with Whisper

  • Model down β€” load models directly fromHugging Face or any URL

  • Conversation-aware preemptive context shifting β€” retain full conversation memory without any message length limits

  • GPU-accelerated inference via Vulkan or Metal β€” runs fast on any OS

  • Compatible with thousands of pre-trained LLMs β€” use any LLM in the GGUF format

  • Powered by the wonderful llama.cpp

We support Kotlin, Swift, Python, Flutter, React Native, Expo and Godot.

Platform Installation Documentation
Kotlin Maven Central docs.nobodywho.ooo/kotlin
Swift SPM docs.nobodywho.ooo/swift
React Native / Expo npm docs.nobodywho.ooo/react-native
Flutter pub.dev docs.nobodywho.ooo/flutter
Python pypi docs.nobodywho.ooo/python
Godot AssetLib docs.nobodywho.ooo/godot
import ai.nobodywho.Chat

val chat = Chat.fromPath(
    modelPath = "hf://NobodyWho/Qwen_Qwen3-0.6B-GGUF/Qwen_Qwen3-0.6B-Q4_K_M.gguf"
)

val response = chat.ask("What is the capital of Denmark?").completed()
println(response) // The capital of Denmark is Copenhagen.

Add to your build.gradle.kts:

// Android
implementation("ai.nobodywho:nobodywho-android:2.0.0")

// Desktop JVM (Linux, macOS, Windows)
implementation("ai.nobodywho:nobodywho:2.0.0")
python
import NobodyWho

let chat = try await Chat.fromPath(
    modelPath: "hf://NobodyWho/Qwen_Qwen3-0.6B-GGUF/Qwen_Qwen3-0.6B-Q4_K_M.gguf"
)

let response = try await chat.ask("What is the capital of Denmark?").completed()
print(response) // The capital of Denmark is Copenhagen.

Add via Swift Package Manager:

https://github.com/nobodywho-ooo/nobodywho-swift.git
js
import { Chat } from "react-native-nobodywho";

const chat = await Chat.fromPath({
  modelPath: "hf://NobodyWho/Qwen_Qwen3-0.6B-GGUF/Qwen_Qwen3-0.6B-Q4_K_M.gguf",
});

const msg = await chat.ask("What is the capital of Denmark?").completed();
console.log(msg); // The capital of Denmark is Copenhagen.

Install via npm:

npm install react-native-nobodywho

npx expo install react-native-nobodywho

RN / Expo documentation - npm - RN starter example app - Expo starter example app

import 'package:nobodywho/nobodywho.dart' as nobodywho;

void main() async {
  await nobodywho.NobodyWho.init();

  final chat = await nobodywho.Chat.fromPath(
    modelPath: 'huggingface:NobodyWho/Qwen_Qwen3-0.6B-GGUF/Qwen_Qwen3-0.6B-Q4_K_M.gguf',
  );

  final msg = await chat.ask('What is the capital of Denmark?').completed();
  print(msg); // The capital of Denmark is Copenhagen.
}

Install via pub.dev:

flutter pub add nobodywho

Flutter documentation - pub.dev - starter example app

from nobodywho import Chat

chat = Chat("huggingface:NobodyWho/Qwen_Qwen3-0.6B-GGUF/Qwen_Qwen3-0.6B-Q4_K_M.gguf")

response = chat.ask("What is the capital of Denmark?").completed()
print(response) # The capital of Denmark is Copenhagen.

Install via pip:

pip install nobodywho

You can install it from inside the Godot editor: In Godot 4.5+, go to AssetLib and search for "NobodyWho".

...or you can grab a specific version from our github releases page. You can install these zip files by going to the "AssetLib" tab in Godot and selecting "Import".

Make sure that the ignore asset root option is set in the import dialogue.

For further instructions on how to setup NobodyWho in Godot please refer to our docs.

The documentation has everything you might want to know: https://docs.nobodywho.ooo/

  • ⭐ Star the repo and spread the word about NobodyWho!
  • Join our Discord orMatrix communities
  • Found a bug? Open an issue!
  • Submit your own PR - contributions welcome
  • Help improve docs, write tutorials and demos

Desktop (Linux, macOS, Windows) is supported across all bindings. Android is supported on Kotlin, Godot, Flutter and React Native. iOS is supported on Swift, Flutter and React Native. visionOS and watchOS are supported via the Swift package.

Web exports will be a bit trickier to get right. See issue #111.

There has been some confusion about the licensing terms of NobodyWho. To clarify:

Linking two programs or linking an existing software with your own work does not – at least under European law – produce a derivative or extend the coverage of the linked software licence to your own work. [1]

You are allowed to use this plugin in proprietary and commercial projects, free of charge.

If you distribute modified versions of the code in this repo, you must open source those changes.

Feel free to make proprietary projects using NobodyWho, but don't make a proprietary fork of NobodyWho.

── more in #large-language-models 4 stories Β· sorted by recency
── more on @nobodywho 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain β€” perfect for shipping the agent you just read about.

$git push zahid main
β†’ Live at https://your-agent.zahid.host βœ“
Get free account β†’ Pricing
from €0/mo Β· no card required
LIVE [news/nobodywho-is-an-infe…] indexed:0 read:4min 2026-09-23 Β· β€”