incoai/splash

A local inference engine for Apple silicon, built around the model.

Open original source ↗

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

[](https://github.com/incoai/splash/actions/workflows/ci.yml) [](LICENSE) [](#quick-start) A local inference engine for Apple silicon, built around the model. Splash serves a small set of models to coding agents and to any OpenAI or Anthropic compatible client, on one Mac. On a 48 GB M5 Pro it decodes Qwen3.8-27B at 2× the speed of the next-fastest engine and, with a 32K context cached, returns the first token in 282 ms. Its kernels, draft model, and memory plan are specialized for each model it serves. That is why it is fast, and why there is nothing to configure. Apple M3 or newer, macOS 26.4 or later, Homebrew, and 36 GB of unified memory (48 GB or more recommended). The first run downloads and verifies the model package, checks available memory, and starts serving on 127.0.0.1:8000. Once it prints Ready, leave this terminal open. Open in your browser, or run an installed coding agent from another terminal:…

incoai/splash on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-09-20T07:41:42.102Z

Inside the original README — Document outline
  1. Splash
  2. Quick start
  3. Use the API
  4. Models
  5. Settings
  6. Performance
  7. Design
  8. More

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

A local inference engine for Apple silicon, built around the model.

Repository facts

Owner
incoai
Primary language
Python
Stars
489
Forks
39
Open issues + pull requests
22
License
Apache-2.0
Archived
No
Default branch
main
Created
2026-09-18T20:01:48.000Z
Last push
2026-09-20T23:13:25.000Z

Topics and intended use

Owner-supplied topics: apple-silicon, coding-agents, llm-inference, macos, metal, speculative-decoding

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-09-21T06:41:42.808Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent