M1 Ultra

mentions 3 type Person feed RSS

// recent coverage 3 mentions

17:09

2026-08-11

sourcefeed.dev

artificial-intelligence

macOS VMs Have Been Sandbagging Your GPU

Cua's Metal capability shim recovers up to 16.36× llama.cpp throughput in macOS virtual machines by unmasking GPU capabilities that Apple's paravirtualized graphics device underreports. On an M1 Ultra…

16:09

2026-08-11

sourcefeed.dev

artificial-intelligence

Your macOS VM's GPU Was Never Slow, Just Mislabeled

Cua, a company building computer-use agent infrastructure on macOS virtual machines, achieved 11–16× faster llama.cpp inference inside Apple Silicon VMs by intercepting Metal capability queries to rep…

14:50

2026-08-11

github.com

machine-learning

Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp

A compatibility layer for Apple's Virtualization.framework released by Cua under a permissive license accelerates LLM inference in macOS virtual machines by 11.08× for prompt processing and 16.36× for…

// co-occurs with top 8 entities

Cua 3 Apple 3 llama.cpp 3 Virtualization.framework 2 TinyLlama 1.1B 2 Google 1 Gemma 4 12B QAT Q4_0 1 MLX 1

// topics top 5 topics

machine learning 3 developer tools 3 artificial intelligence 2 ai infrastructure 1 large language models 1