Squish

Fastest way to run local LLMs on Apple Silicon, sub-second model loads.

Desktopfreeglobal

Squish is a local LLM runtime for Apple Silicon offering sub-second model loads and better throughput, tail latency and full-response time than Ollama, with an OpenAI/Ollama-compatible interface and no cloud or API keys. It's aimed at Mac users who want the fastest possible local LLM inference on their own hardware.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Squish - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Squish to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Squish (or something else) actually fits.

Try a problem