CUDA, Shmuda: Fold Proteins on a MacBook
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Alphafold3 used to be fodder for HPC clusters; now I've got a port running smoothly on Apple Silicon. If you have an M-series Mac (~2023-present), you can generate protein structures from sequences in minutes. Give it a try!GitHub repo: https://github.com/latent-spacecraft/openfold-3-mlx
HN · launched Nov 17, 2025 · 11 upvotes (top 46%) · 0 views
Niche: computational biology and chemistry software · 119 launches, 7 in the last 7 days ▲ +17% · Explore this niche →
Category and tags
- Healthcare
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 119 launches in computational biology and chemistry software →
Could you build this?
No Porting complex molecular biology deep learning architectures like AlphaFold 3 to Apple MLX requires deep knowledge of structural bioinformatics, tensor math, and low-level GPU kernel optimization.
What it would actually take: This project entails rewriting AlphaFold 3 / OpenFold architectures from PyTorch/CUDA into Apple's MLX framework. The hard parts include reimplementing complex Evoformer and diffusion modules, writing custom Metal Performance Shaders (MPS) kernels for pair representations and invariant point attention, and managing unified memory allocations to fit multi-chain molecular models into Mac RAM.
Discussion
3 comments analyzed.
Competitors mentioned: OpenFold
Concerns raised: RAM limitations restricting protein size to <1500 residues, MSA and template handling complexity
Feature requests: Support for very large proteins/complexes using Mac VRAM
Competitors
Other products that read as similar to this one : 66 launches clear the similarity bar, closest 8 shown.
Attention rank: #37 of 67 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 4 days after the earliest competitor.
- picofold · github · 2026-10-05 · 19 upvotes · similarity 0.46
- mvcc · github · 2026-09-23 · 51 upvotes · similarity 0.46
- macuda · github · 2026-09-16 · 30 upvotes · similarity 0.42
- Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon · hn · 2026-04-20 · 202 upvotes · similarity 0.41
- keys-Mac-TensorFold-MiniMax-H3-MLX · github · 2026-10-04 · 26 upvotes · similarity 0.40
- reticulumOverVHF · github · 2026-09-15 · 11 upvotes · similarity 0.38
- twinfold · github · 2026-10-23 · 51 upvotes · similarity 0.38
- PrintLab · github · 2026-11-11 · 299 upvotes · similarity 0.38
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.