Skip to main content
Back to resources
Inference🚀

Tokspur

Released on Nov 10, 2026

Open source inference engine for Apple Silicon built on Metal: claims decode up to three times faster than classic engines on MacBook and Mac Studio. Young project, no independent benchmarks yet.

Features

  • Apple Silicon (Metal)
  • Open source
  • Claim: ~3x decode vs classic engines

Tags

Useful links

Discover Tokspur

Visit the official site to download, learn more and start using Tokspur.

Visit the site

Related resources — Inference

Inference⚡
llama.cpp
Released Oct 15, 2022

C++ implementation of LLMs for efficient inference on consumer CPUs and GPUs.

LLMC++LocalEfficient
Inference🦙
Ollama
Released Jul 27, 2023v0.35.0

Open source tool to run LLMs locally with simplicity.

LLMLocalOpen SourceCLI
Inference🗣️
Piper TTS
Released Apr 1, 2022Piper

Sintesi vocale in locale a bassa latenza basata su ONNX: genera parlato naturale da testo in tempo quasi reale, anche su CPU. Multilingue (italiano incluso) e facile da integrare nei pipeline: download del modello, una riga di comando. MIT.

AudioTTSOpen SourceLocale