nowfound

Dev tools · April 20, 2026

RT

Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon

I ported Microsoft's TRELLIS.2 (4B parameter image-to-3D model) to run on Apple Silicon via PyTorch MPS. The original requires CUDA with flash_attn, nvdiffrast, and custom sparse convolution kernels: none of which work on Mac. I replaced the CUDA-specific ops with pure-PyTorch alternatives: a gather-scatter sparse 3D convolution, SDPA attention for sparse transformers, and a Python-based mesh extraction replacing CUDA hashmap operations. Total changes are a few hundred lines across 9 files. Generates ~400K vertex meshes from single photos in about 3.5 minutes on M4 Pro (24GB). Not as fast as…

In plain words

Run TRELLIS.2 is a port of Microsoft's image-to-3D model that runs natively on Apple Silicon using PyTorch MPS instead of requiring CUDA. It converts single photographs into detailed 3D meshes with approximately 400,000 vertices in about 3.5 minutes on M4 Pro hardware. The project replaces GPU-specific operations with pure-PyTorch alternatives, enabling offline 3D generation without cloud dependency. It is designed for developers and creators working on Apple computers who need local 3D model generation from images.

written from the facts on this page · September 2026

From the sources

In the maker’s words, at launch

I ported Microsoft's TRELLIS.2 (4B parameter image-to-3D model) to run on Apple Silicon via PyTorch MPS. The original requires CUDA with flash_attn, nvdiffrast, and custom sparse convolution kernels: none of which work on Mac. I replaced the CUDA-specific ops with pure-PyTorch alternatives: a gather-scatter sparse 3D convolution, SDPA attention for sparse transformers, and a Python-based mesh extraction replacing CUDA hashmap operations. Total changes are a few hundred lines across 9 files. Generates ~400K vertex meshes from single photos in about 3.5 minutes on M4 Pro (24GB). Not as fast as H100 (where it takes seconds), but it works offline with no cloud dependency. https://github.com/shivampkumar/trellis-mac

More dev tools this month

the category →
  • Dograh592

    The open source VAPI alternative

    Dev tools · 25d ago · dograh.com

  • Meridian530

    Don't let your work go unnoticed. Get promoted!

    Dev tools · 20d ago · meridiona.com

  • x1516

    Lovable for iPhone apps go from idea to App Store

    Dev tools · 11d ago · x1.new

  • Open-source GTM skills for technical founders

    Dev tools · 29d ago · gtmcofounder.com

  • OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.

    Dev tools · 2d ago · opentrailpaper.com

  • Nuphos380

    The AI-Native DevOps Workspace.

    Dev tools · 24d ago · nuphos.ai

Launched alongside, April 2026

the whole month →
  • Brila1,367

    One-page websites from real Google Maps reviews

    AI · Apr 2026 · brila.ai

  • AG

    Thought the resources for GPU arch were lacking, so here we are

    Life & fun · Apr 2026 · jaso1024.com

  • IB

    Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

    AI · Apr 2026 · github.com

  • AI meeting notes: now bot-free, in ChatGPT & Claude + more

    AI · Apr 2026 · fathom.ai

  • BC

    Life & fun · Apr 2026 · sam-burns.com

  • IB

    With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

    AI · Apr 2026 · text.blogosphere.app