--- title: GitHub - shivampkumar/trellis-mac | daily.dev description: A port of Microsoft's TRELLIS.2 image-to-3D model to Apple Silicon using PyTorch MPS, eliminating the CUDA dependency. The port replaces CUDA-only libraries... canonical: https://daily.dev/posts/github---shivampkumar-trellis-mac-vayzxbmie twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: GitHub - shivampkumar/trellis-mac | daily.dev og:description: A port of Microsoft's TRELLIS.2 image-to-3D model to Apple Silicon using PyTorch MPS, eliminating the CUDA dependency. The port replaces CUDA-only libraries... og:url: https://daily.dev/posts/github---shivampkumar-trellis-mac-vayzxbmie og:image: https://api.daily.dev/og/posts/vAYZxBmiE.png og:image:alt: GitHub - shivampkumar/trellis-mac og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # GitHub - shivampkumar/trellis-mac **[Hacker News](https://daily.dev/sources/hn)** · 4 min read · 0 upvotes · 0 comments ## Summary A port of Microsoft's TRELLIS.2 image-to-3D model to Apple Silicon using PyTorch MPS, eliminating the CUDA dependency. The port replaces CUDA-only libraries (flex_gemm, flash_attn, nvdiffrast, cumesh) with pure-PyTorch and pure-Python alternatives. On an M4 Pro with 24GB unified memory, it generates 400K+ vertex meshes from a single image in ~3.5 minutes. Key limitations include no texture export (requires nvdiffrast), disabled hole filling, and ~10x slower sparse convolution compared to CUDA. Setup requires Python 3.11+, 24GB+ RAM, and ~15GB disk space for model weights. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac](https://daily.dev/posts/show-hn-open-source-engine-running-gemma-4-26b-in-2-gb-ram-on-any-m-series-mac-nwy9umvdc) · Hacker News · 0 upvotes · 0 comments - [Teaching Automatic1111 to Speak Metal on an M1](https://daily.dev/posts/teaching-automatic1111-to-speak-metal-on-an-m1-45rpgxe1o) · Hacker News · 0 upvotes · 0 comments - [Running PyTorch Models on Apple Silicon GPUs with the ExecuTorch MLX Delegate – PyTorch](https://daily.dev/posts/running-pytorch-models-on-apple-silicon-gpus-with-the-executorch-mlx-delegate-pytorch-thejyz1bz) · PyTorch · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#python](https://daily.dev/tags/python), [#pytorch](https://daily.dev/tags/pytorch) [View this post on daily.dev](https://daily.dev/posts/github---shivampkumar-trellis-mac-vayzxbmie) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"GitHub - shivampkumar/trellis-mac","url":"https://daily.dev/posts/github---shivampkumar-trellis-mac-vayzxbmie","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/github---shivampkumar-trellis-mac-vayzxbmie"},"datePublished":"2026-04-20T04:16:32.523Z","dateModified":"2026-04-20T04:16:55.339Z","description":"A port of Microsoft's TRELLIS.2 image-to-3D model to Apple Silicon using PyTorch MPS, eliminating the CUDA dependency. The port replaces CUDA-only libraries...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/58ca9141d478a5c5ebdc0ee8ebcbffda?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/58ca9141d478a5c5ebdc0ee8ebcbffda?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/github---shivampkumar-trellis-mac-vayzxbmie","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,python,pytorch","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"GitHub - shivampkumar/trellis-mac"}]} ```