incoai / splash
A local inference engine for Apple silicon, built around the model.
Why this job: says: inference engine, local inference; topics: apple-silicon, llm-inference
What it does
Splash runs coding agents and OpenAI or Anthropic compatible applications on one Mac. It combines DFlash 2 speculative decoding, specialized Metal kernels, and automatic memory planning, with vision, tool calling, and a built-in chat page. It reuses cached prefixes and batches concurrent requests automatically.
Get started
brew install incoai/tap/splash
splash serve --model unsloth/Qwen3.8-27B-GGUF:UD-Q4_K_M - Maintenance
- Active
- Last commit 4 days ago
- Stars
- 2,170
- +114 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- Mac
- From the latest release
- Latest version
- 1.6.0
- Released 4 days ago
- Built with
- C++
- 44% of the code
Is it looked after?
- Contributors
- 5
- Last 90 days
- Issues
- 66% closed
- 86 still open
- Pull requests
- 303 merged
- 72 waiting
- Releases
- 13
- 13 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| vllm-project / vllm-metal | 1,979 | yesterday | Apache-2.0 | Mac |
| StayLameBro / backburner | 1,174 | 3 days ago | MIT | No downloads |
| jundot / omlx | 23,491 | 5 days ago | Apache-2.0 | Mac |
More: download files, languages, topics and project record
Languages
- C++ 44%
- Python 27%
- Objective-C++ 19%
- Swift 4%
Topics
- apple-silicon
- coding-agents
- llm-inference
- macos
- metal
- speculative-decoding
Project record
- JobLocal LLMs
- StatusListed
- Commits1,599
- Forks214
- Watching20
- Stars in 28 days+753
- CreatedSep 18, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026