# lostmsu/TurboGPT

> Trains a tiny byte-level GPT from scratch in CUDA C++ in under a minute; suited for experimenting with language model training on a local GPU.

- Magnitude: 2.7 out of 10 — Steady
- Stars: 19 total · +19 stars today
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: MIT · Created: 2026-09-23 · Last push: 2026-09-29
- GitHub: https://github.com/lostmsu/TurboGPT · Page: https://gitnova.dev/en/r/lostmsu/TurboGPT

## Useful for

- Train a mini-GPT on a custom text file and get a checkpoint for further fine-tuning
- Resume interrupted training from a saved checkpoint using --load
- Check model quality via BPB metric on the hn1g dataset

## Why it’s here

- 19 stars today.
- The repository is 6 days old and already has 19 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: TurboGPT: train 22KiB transformer in 13s” — 36 points, 3 h ago.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 3 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 9
- Latest release: v0.0.1 (2026-09-29)

## Stars per day, last 10 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-29: 0, 0, 0, 0, 0, 0, 0, 0, 0, 19

## Hacker News

- Show HN: TurboGPT: train 22KiB transformer in 13s — 36 points, 5 comments: https://news.ycombinator.com/item?id=49898931

## Spotted in now

- Spotted on Hacker News

## Similar by description

1. **volotat/mini-AGI** — 1.5 · Cooling · Language models · Python · +7 stars today
   A byte-level continual-learning language model that assembles its own architecture, trains from scratch on a single 8 GB VRAM GPU, and keeps learning from everything it reads. An experiment showing continual learning without catastrophic…
   Full card: https://gitnova.dev/en/r/volotat/mini-AGI.md
2. **microsoft/SkillOpt** — 3.5 · Breakout · AI agents · Python · +52 stars today
   A text-space optimizer that trains reusable natural-language skills for frozen LLM agents via trajectory-driven edits, validation-gated updates, and a deployable best_skill.md artifact. Model weights stay untouched.
   Full card: https://gitnova.dev/en/r/microsoft/SkillOpt.md
3. **jingyaogong/minimind** — 2.5 · Cooling · Language models · Python · +40 stars today
   An open-source educational project for training a tiny 64M-parameter LLM (MiniMind) from scratch in PyTorch, covering the full pipeline: pretrain, SFT, LoRA, RLHF, RLAIF and Tool Use.
   Full card: https://gitnova.dev/en/r/jingyaogong/minimind.md
4. **MrNeRF/LichtFeld-Studio** — 1.5 · Steady · Generative media · C++ · +5 stars today
   A native application to train, inspect, edit, and export 3D Gaussian Splatting scenes, with Python plugins and MCP-driven automation. Requires an NVIDIA GPU with CUDA 12.8+.
   Full card: https://gitnova.dev/en/r/MrNeRF/LichtFeld-Studio.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-29 23:01 UTC, updated every 30 minutes.