AI & ML interests

AI created with RustingBrain for consumer class GPUs

Recent Activity

RustingStudio  updated a Space 5 days ago
rusting-studio/README
RustingStudio  published a Space 5 days ago
rusting-studio/README
View all activity

Organization Card

RustingStudio

We build machine-learning software in Rust and train our own models on consumer hardware. Everything here was trained from scratch on a single RTX 3060 12 GB, with no Python in training or in use. The code is open:

  • RustingBrain: the deep-learning library the models are trained with.
  • RustingRunner: the small program that runs the released weights.
  • RustingStrata: an inference engine for Qwen GGUF models.

Models

Kaze-3D-v0.1: one image in, one 3D mesh out, in 4 seconds on an RTX 3060. An early release: it gets the rough shape of an object, geometry only. Apache-2.0, trained only on CC-BY and CC0 data. The model page has the measured numbers and the limits.

More at rustingstudio.com and github.com/RustingStudio.

datasets 0

None public yet