---
title: "S&Box LLM Proof of Concept - s&box game"
description: "Proof of concept for running a real LLM entirely inside s&box using a custom C# GPT-Neo inference engine. No APIS, fully local"
canonical: "https://sbox.watch/ru/games/jeffskitchen/llm_poc/"
generated_at: "2026-10-09T14:45:19.818Z"
---

# S&Box LLM Proof of Concept

Proof of concept for running a real LLM entirely inside s&box using a custom C\# GPT-Neo inference engine. No APIS, fully local

- Тип: игра
- Идентификатор: jeffskitchen.llm_poc
- Автор: jeffskitchen
- Канонический URL: https://sbox.watch/ru/games/jeffskitchen/llm_poc/
- Markdown: https://sbox.watch/ru/games/jeffskitchen/llm_poc/index.md
- sbox.game: https://sbox.game/jeffskitchen/llm_poc/
- Создано: 2026-10-09T14:45:19.818Z

## Статистика

- Играют сейчас: 0
- пик игроков за 24 ч: 0
- динамика за 24 ч: +0
- Terry Score: 13%
- Избранное: 4
- Положительные оценки: 3
- Отрицательные оценки: 7
- Всего игроков: 25
- Всего сеансов: 29
- Суммарное время игры: 1,7 часов
- Прирост времени игры за последние 7 дней: 3 минуты
- Исходное значение времени игры за 7 дней: 2026-10-02T06:49:21.208Z
- Обновлено: 17 авг. 2026 г.
- Создано: 17 авг. 2026 г.
- Размер: 32.1 MB
- Файлы: 41
- Теги: llm

## Описание

!!!!NOTE!!!!!!:
This is not meant to be even a tiny bit close to an actual useable ChatGPT or Claude clone, the model (TinyStories-Instruct-1M) is quite literally 1/2000 the size of any flagship model. The findings in this project can be used to build larger language model projects.

S&Box LLM POC is a proof of concept demonstrating that a transformer language model can run entirely inside the s&box game runtime without external AI software, servers, APIs, Python, Ollama, or separate executables.

The project includes a custom C\# inference engine capable of loading packaged model weights, GPT-2 tokenization, GPT-Neo transformer inference, global and local attention, and autoregressive text generation directly within s&box.

The current implementation runs TinyStories-Instruct-1M locally on the CPU and has been numerically validated against the original PyTorch/Hugging Face model. Generated token sequences match the reference implementation while inference runs on an s&box worker thread to keep the game responsive.

The end goal of the POC is a simple in-game chat interface powered entirely by an LLM running inside s&box itself.

From this, I hope other developers can see what is possible and potentially use small LLM to power NPCs, game functions or even whole games.




## More by jeffskitchen

| Package | Идентификатор | Игроки | Избранное | Положительные оценки | Оценка | Markdown |
| --- | --- | --- | --- | --- | --- | --- |
| AI Decision Maker (GLiNER 2.5) | jeffskitchen.aidecisionmakergliner25 | 0 | 1 | 0 | -- | https://sbox.watch/ru/games/jeffskitchen/aidecisionmakergliner25/index.md |