Metal-Gauss trains 3D Gaussian splats on Mac in minutes, no CUDA needed, beats msplat on PSNR-per-minute
CSProfKGD · x · 2026-09-02
NandoMetzger released Metal-Gauss, an open-source project that trains 3D Gaussian Splatting natively on Apple Silicon using Metal kernels compiled at runtime — no CUDA, no Xcode, just Command Line Tools. It may be the fastest Mac-native Gaussian optimizer to date.
Benchmarked on all 8 NeRF-synthetic scenes with identical seed clouds on the official 200-view test split, it dominates on quality-per-minute: PSNR 21.5 at 30 seconds (vs 12.8-19.9 for msplat, Brush, spirula), 29.8 at 3 minutes, and converges to 31.9 within 15 minutes. Code is on GitHub and contributions are welcome.
More from Infra
- Dell COO: inference tokens to grow 87x to 3,600 quadrillion by 2030 — Beth_Kindig · 2026-09-03
- SkyPilot launches Agent Sessions: coding agents keep running on your own K8s after you disconnect — skypilot_org · 2026-09-03
- Beating hipBLASLt on a gaming GPU: a GEMM optimization deep dive — Moist_Weird_42067 · 2026-09-03
- Modal intern's recap: environment-level budgets and agent-driven RL post-training — dejavucoder · 2026-09-03
- Edge AI won't kill cloud CapEx: five arguments against the cloud-killer narrative — yangastas_paradise · 2026-09-03
- Saving on Google Photos with self-hosted Immich: a personal photo storage walkthrough — speckx · 2026-09-03