Skip to content
Tech News
← Back to articles

Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM

read original get NVIDIA GeForce RTX 4060 GPU → more articles
Why This Matters

This project explores whether a continual-learning language model can be trained from scratch on consumer-grade hardware (an 8GB VRAM GPU) without suffering catastrophic forgetting, a core limitation of today's frozen, pre-trained LLMs. While it's a small toy model rather than a frontier system, it points toward a future where individuals could own and continuously train their own personalized models rather than relying solely on large corporations' fixed models.

Key Takeaways
Worth a Look

NVIDIA GeForce RTX 4060 GPU — This project is designed to run on an 8GB VRAM GPU, and the RTX 4060 hits that mark while remaining affordable for hobbyists experimenting with local model training. It's a solid entry point for anyone wanting to try continual learning experiments like mini-AGI on their own desktop without needing a data-center card.

See NVIDIA GeForce RTX 4060 GPU on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.

mini-AGI - is a continual learning byte-level language model that assembles its own architecture, trains from scratch on a single 8 GB VRAM GPU, and keeps learning from everything it reads. It stores its weights as ordinary files on disk and pages them onto the card as it needs them, so the parameter count is bounded by free disk space rather than by VRAM. It grows new capacity while training when it runs short, prunes what nothing asks for, and reads through exactly the same code path it serves on. Targeted at a PC or laptop with at least an 8 GB VRAM GPU on the board.

NOTE: as of now this is a small toy-level model. Do not expect a frontier level capabilities. This is rather a small experiment to show, that continual learning from the single stream of data without catastrophic forgetting is possible. Furthermore it is possible on a modest hardware. Which means that almost everyone could train their own version of the model (or simply continue training this one) exactly as they see it fit. And the capabilities would be bounded by the actual hardware, scale and quality of the data available and the amount of time one willing to spend on training the model.

Here is how min-run dashboard looks like. The model is pointed to the corpus to constantly read and learn from.

History - here is the samples from the whole training run history so far. You can inspect them yourself to see how the model improved over the course of training/reading the corpus.

The weights are not published yet. The run is still reading its first pass over the corpus, the weights go up once it has been through all of it, which is a couple of weeks away at the current rate.

Motivation

Every language model you can actually own today is a model somebody else trained and then froze. You can fine-tune around the edges of it, but you cannot train one from scratch on your own hardware, and you cannot keep training it on what you do day to day - the moment you try, it forgets what it knew before. The result is that a personal model is always somebody else's model with a thin layer of you on top, and it stops learning the day it ships.

mini-AGI model has small enough GPU footprint that it is possible to train end-to-end on one consumer card, and it is built so that training never has to stop. It reads a stream of characters one chunk at a time, takes a gradient step on each, and the same path serves generation. There is no separate fine-tuning regime and no frozen base: reading and being trained are the same event.

Three constraints shape everything else in the design:

It has to fit on 8 GB. Not with quantisation - training needs gradients and optimiser state, which is roughly three times the weights again. So the weights live on disk and only the working set is resident.

... continue reading