brontoguana / krasis
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
Why this job: topics: llm-inference, inference-engine
What it does
Krasis is built by Northloom. Need help running AI locally? Northloom offers local and self-hosted AI inference consulting, including model selection, GPU hardware planning, inference performance optimisation, architecture reviews and ongoing technical advice.
Get started
curl -sSf https://krasis.ai/downloads/install.sh | bash You need: Krasis currently targets NVIDIA GPUs with CUDA, including Ampere and newer; Input models should be BF16 safetensors from Hugging Face or another local; First run is slower because Krasis builds optimized local caches. Later runs
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 527
- +3 this week
- Licence
- Custom
- Read before business use
- Downloads for
- 2 systems
- Windows, Linux
- Latest version
- v1.0.23
- Released 2 days ago
- Built with
- C++
- 48% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 59% closed
- 11 still open
- Pull requests
- 0 merged
- 8 waiting
- Releases
- 169
- 30+ in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| EfficientMoE / MoE-Infinity | 382 | 3 days ago | Apache-2.0 | Linux |
| peonist-ai / halogen-flash-server | 1,275 | yesterday | Custom | No downloads |
| xLLM-AI / xllm | 1,619 | yesterday | Apache-2.0 | No downloads |
More: download files, languages, topics and project record
Download files, v1.0.23
- Windows3 files, 5 downloads
- Linux4 files, 6 downloads
Languages
- C++ 48%
- Rust 30%
- Python 11%
- HTML 4%
Topics
- cpu-inference
- gguf-model-support
- gpu-inference
- high-performance-inference
- hybrid-inference
- inference-engine
- inference-optimization
- large-language-models
- llama-cpp-alternative
- llm-inference
- mixture-of-experts
- transformer
Project record
- JobLocal LLMs
- StatusListed
- Commits827
- Forks33
- Watching10
- Stars in 28 days+7
- CreatedFeb 9, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026