π Our Goal
To make models run on actual consumer hardware at speeds and intelligence that feel closer to the cloud.
π What We Believe
We believe real local AI should run on hardware people can actually own or already own, not just on so-called consumer hardware that is too expensive or out of reach for most. GPUs like the RTX 3090, 4090, and 5090, along with unified systems such as NVIDIA DGX Spark, AMD AI Halo, and high-end Mac Studios and Mac minis, are powerful, but they are far from what most people, especially average enthusiasts and students, have sitting on their desks.
π What We Do
We take existing model and prune, merge, finetune and quantize them to compress while retaining as much intelligence as possible for limited hardware. The objective is not to make a small model enough just for the sake of fitting. It is to make it small in a controlled, tested efficient way with doesn't lobotomizes the model's capabilities for local agentic tasks. Thus why we believe is Runnable β Usable.
π Open Research
All our research, techniques, methods, experiments, and datasets will be open sourced. We believe useful AI should be built for the community, by the community.
A practical hardware scale outlining the minimum, recommended, and higher-end consumer systems suitable for running our models.
| Tier Size | Target Hardware | Purpose |
|---|---|---|
π₯ ~16GB | Higher-end consumer GPUs and unified-memory systems | Maximum Quality and Fast Prompt Processing at 256k Context |
π₯ ~12GB | Fairly High-end consumer GPUs (Our Recommended Tier) | High Quality and Fast Prompt Processing at 128k Context |
π₯ ~10GB | Budget mid-range consumer GPUs | High Quality and Moderate Prompt Processing at 96k Context |
π
~8GB | Fairly budget-oriented consumer GPUs | Balanced Quality and Moderate Prompt Processing at 64k Context |
π
~6GB | Extremely common low end budget consumer GPUs | Balanced Quality and Prompt Processing at 64k Context |
Sorazium Labs and its currently released models are independently developed and operated by AceTheUnfazed. A small disclaimer, Iβm simply a local AI enthusiast who enjoys experimenting, learning, and building in this space. Iβm not a large AI company or research organization, so any suggestions, technical advice, feedback, contributions, or other forms of support go a long way and are genuinely appreciated. If youβre interested in contributing to or joining Sorazium Labs, collaborating on projects, sharing ideas, or helping with research and development, feel free to reach out at [labs@sorazium.com](mailto:labs@sorazium.com). Thank you to everyone who supports Sorazium Labs and the Local AI Community!