TinyGPU brings eGPUs to Mac AI

// 67d agoTUTORIAL

TinyGPU brings eGPUs to Mac AI

TinyGPU is a tinygrad runtime that lets supported AMD and NVIDIA GPUs attach to macOS over USB4/Thunderbolt for AI workloads. The docs walk through driver installation, compiler setup, and running tinygrad apps on the external GPU.

// ANALYSIS

This is a clever infrastructure hack, not a consumer-friendly plug-and-play feature, but it meaningfully widens the hardware options for Mac-based AI work.

–Supports AMD RDNA3+ and NVIDIA Ampere+ cards on macOS 12.1+ over Thunderbolt or USB4
–Uses tinygrad’s own driver and compiler setup, so the stack matters as much as the hardware
–Best suited to researchers and tinkerers who want a Mac front end with discrete GPU compute attached externally
–Could soften the Mac versus NVIDIA workstation tradeoff for local inference and prototyping
–Still niche: the GPU, OS, and setup constraints keep it in power-user territory

// TAGS

tinygpugpuinferenceopen-sourceself-hosteddevtool

DISCOVERED

67d ago

2026-04-04

PUBLISHED

67d ago

2026-04-04

RELEVANCE

8/ 10

AUTHOR

Historical-Health-50

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE3m ago

OpenMed 1.5.5 adds batch PII processing

OpenMed version 1.5.5 introduces batch PII extraction and de-identification alongside REST model unload and keep-alive controls. The update also improves Swift-based on-device acceleration and clinical OCR document handling on Apple Silicon.

NEWS13m ago

Claude Code creator highlights shift to agentic loops

Boris Cherny, the creator of Anthropic's Claude Code, shared that his engineering workflow has shifted from writing traditional prompts to building autonomous loops. Developers now build agentic systems that run continuously to discover, execute, and verify tasks independent of constant user input.

UPDATE45m ago

Netlify launches an official plugin in the Cursor marketplace to provide AI models with native context on Netlify functions, databases, and deploys.

Netlify has released an official integration in the Cursor Marketplace, bringing developer-focused capabilities directly into the Cursor IDE. The plugin includes 13 skills and 27 rules to give Cursor's AI models precise context regarding Netlify's features, such as functions, edge functions, Blobs, Database, caching, the AI Gateway, CLI, and deployments.