splash is an open-source LLM inference tool written in C++, released under the Apache-2.0 license. It has 1.5k GitHub stars and 147 forks, and was last updated in October 2026. Docs and downloads are linked from inco.ai.
“A local inference engine for Apple silicon, built around the model.”
— incoai, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 1,540 |
| Forks | 147 |
| Language | C++ |
| License | Apache-2.0 |
| Last updated | |
| Owner | incoai |
| Website | inco.ai/blog/splash |
| Repository | incoai/splash |
Tags
apple-siliconcoding-agentsllm-inferencemacosmetalspeculative-decoding
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.