# brontoguana/krasis

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/brontoguana-krasis).**

476 stars · 27 forks · C++ · NOASSERTION

## Links

- GitHub: https://github.com/brontoguana/krasis
- awesome-repositories: https://awesome-repositories.com/repository/brontoguana-krasis.md

## Description

Krasis is an LLM runtime for running large MoE models on NVIDIA consumer GPUs. It is built around fast GPU prompt processing, GPU-executed decode, and HCS expert residency management so models much larger than VRAM can still run locally.

## Tags

### Part of an Awesome List

- [Inference Engines](https://awesome-repositories.com/f/awesome-lists/ai/inference-engines.md) — Hybrid runtime for running large models on limited VRAM.