Nvidia · Apple · FTC · AMD · macOS · AI Inference · scottjg.com
RTX 5090 and M4 MacBook Air: Can It Game?
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Sadly, if your main objective is to run AI inference or play games, tinygrad probably isn’t the solution you’re looking for.
Key facts
- Ok, so the plan is to plug a big PC gaming GPU, an NVIDIA RTX 5090, into their M4 MacBook Air
- You get 4 PCIe lanes at up to 40Gbps on Thunderbolt 4, with a small performance penalty for the tunneling
- There’s nothing they can do about it, and it’s still ~30x faster than trapping every access, but it makes writing the BAR ~10x slower than it would be normally
- You can run Linux in a 64-bit ARM VM on a macOS host. macOS supports Thunderbolt devices
Summary
Never tell me the odds What’s a Thunderbolt eGPU? What about tinygrad? Engineering PCI Passthrough on macOS PCI device basics Mapping PCI BARs DMA DMA on Apple Silicon apple-dma-pci NVIDIA alignment quirk Coalescing mappings Other performance concerns Scheduling Total store ordering. Benchmarks CPU comparison Cyberpunk 2077 720p Low 1080p 4K Takeaways GravityMark Shadow of the Tomb Raider Horizon Zero Dawn Remastered Doom (2016) Can it run Crysis? What if you could strap a full desktop GPU to your MacBook Air? A quick FTC required note: When you buy through their links, the reporter may earn a commission.