README / README.md
SectileRon's picture
Org card: one product image
01287c2 verified
|
Raw History Blame Contribute Delete
1.49 kB
---
title: README
emoji: ⬛
colorFrom: gray
colorTo: gray
sdk: static
pinned: false
---
<p align="center">
<img src="https://huggingface.co/spaces/SectileLabs/README/resolve/main/sectile-banner.png" alt="Sectile Research Laboratories. We build the model, and everything it runs on." width="100%">
</p>
**Sectile Research Laboratories** is rebuilding the AI stack from the representation up. We release consumer-focused versions of the systems we run on to the open-source and local-hosting community.
<p align="center">
<img src="https://huggingface.co/spaces/SectileLabs/README/resolve/main/products.png" alt="GInfer: open-source inference engine for fast, high-concurrency, long-context work on NVIDIA GPUs, Apache 2.0. GChat: the desktop app for GInfer on Windows and Linux." width="100%">
</p>
## Models
The [GInfer Models](https://huggingface.co/collections/SectileLabs/ginfer-models-6aa0682395e628be98a798ef) collection holds our model packages for GInfer and GChat. Each package's card names its base model and license.
| Format | What it is | GPUs |
|---|---|---|
| INT | 4-bit groupwise integer | Ampere, Ada, Blackwell |
| NVFP4 | 4-bit NVIDIA FP4 | Blackwell (RTX 50 series, RTX PRO) |
| SMOL | 2-bit, mixed with 4-bit where a model needs it | Ampere, Ada, Blackwell |
The packages run only in GInfer and GChat.
## Learn more
- [sectilelabs.ai](https://sectilelabs.ai)
- [Case study: building GInfer with Quaestor](https://sectilelabs.ai/case-study-ginfer.html)