Alternatives
Products that do what Apple's SHARP running in the browser via ONNX runtime web does
Hi HN, author here. SHARP is Apple's recent single-image 3D Gaussian splatting model (https://arxiv.org/abs/2512.10685). Their reference code is PyTorch + a pretty heavy pipeline; I wanted to see if it could run in a browser with no server hop, so I exported the predictor to ONNX and ran it via onnxruntime-web with the WebGPU EP. What works: drop in an image, get a .ply you can download or preview live, all on your machine — your image never leaves the tab. The model is large (~2.4 GB sidecar) so first load is slow on a cold cache, but inference itself is a few seconds on…
- 1RT
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…
Apr 2026 · github.com
- 2RT
2023 · antimatter15.com
- 3
- 4OS
Hi HN, I built a specialized inference engine for running 4-bit Gemma 4 26B-A4B-IT on any M-series Mac using about 2 GB of RAM. It is called TurboFieldfare and is written in Swift and Metal. I have always adored on-device AI. It feels like magic that you can run a powerful NN on your Mac or iPhone. So I wanted to push the limits a bit and run a model whose weights don’t fit in memory. The model’s 4-bit quantized weights occupy roughly 14 GB, which makes running it with conventional inference tools almost impossible on an 8 GB or even 16 GB Mac once the OS, applications, and KV cache are…
Jul 2026 · github.com
- 5SA
I'm the co-creator and maintainer of https://aframe.io/ and long time Web 3D graphics dev. Super excited about new techniques to author / render / represent 3D. Spark is a an open source library to easily integrate Gaussian splats in your THREE.js scene I worked with some friends and I hope you find useful. Looking forward to hearing what features / rendering techniques you would love to see next.
2025 · sparkjs.dev
- 6GS
The Setup: https://i.imgur.com/o0hgybh.jpeg https://i.imgur.com/mcNiomp.jpeg https://i.imgur.com/vIjw6pc.jpeg https://i.imgur.com/nzOwmSC.jpeg
May 2026 · superspl.at
- 7
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
27d ago · cactuscompute.com
- 8IC
Hi, I'm a developer and first time i shipped the real product after observing the startups and indie hackers community for years. I had made so many useless apps [you should check my website https://ansh.life], but this time I built a very useful product that has a number of super easy-to-use tools in one app for video, music, and photo files. Users can compress, convert, resize, and do so much more with easy-to-use tools. Background: I developed a frame-by-frame video cropper to upload cropped landscape videos to Instagram Reels. However, it required FFmpeg, and as a noob video…
2025 · pimosa.app
- 9SO
2024 · playcanvas.com
- 10AR
I’ve been experimenting with Rust lately and wanted a project that would help me explore some of its lower-level and performance-oriented features. Inspired by Sebastian Lague’s videos, I decided to implement my own ray tracer from scratch. The initial goal was just to render a simple 3D scene in the browser at a reasonable frame rate. It evolved into a small renderer that can: • Run locally or on the web using wgpu and WebAssembly • Perform mesh rendering with a Bounding Volume Hierarchy (BVH) for acceleration • Simulate both direct and indirect illumination for photorealistic results • Be…
Nov 2025 · github.com
- 11
- 12TA
Apr 2026 · blog.playcanvas.com
- 13
- 14IR
Jun 2026 · github.com
- 15
- 16RT
LiveSplat is a system for turning RGBD camera streams into Gaussian splat scenes in real-time. The system works by passing all the RGBD frames into a feed forward neural net that outputs the current scene as Gaussian splats. These splats are then rendered in real-time. I've put together a demo video at the link above.
2025
- 17IR
Jul 2026 · github.com
- 18BA
Hello HN! I want to share something me and a few friends have been working on for a while now — Zeroshot, a web tool that builds image classifiers using text-image models and autolabeling. What does this mean in practice? You can put together an image classifier in about 30 seconds that’s faster and more accurate than CLIP, but that you can deploy yourself however you’d like. It’s open source, commercially licensed, and doesn’t require you to pay anyone per API call. Here's a 2 minute video that shows it off: https://www.youtube.com/watch?v=S4R1gtmM-Lo How/why does it…
2023 · usezeroshot.com
- 19M3
Grant Sanderson (3Blue1Brown) created Manim, the Python library he uses to make the math animations in his videos. We reimplemented Manim with the same Python API, but the implementation underneath is Rust, connected to Python through PyO3. The Rust code uses wgpu, so rendering happens on the GPU. To run it in the browser, we compiled the Rust parts to WebAssembly so the PyO3 extension loads in Pyodide. In the browser, wgpu targets the WebGPU API, so animations render in real time on your GPU through the browser. The editor is Monaco (the editor that powers VS Code) with a live preview:…
Jul 2026 · studio.academa.ai
- 201M
Written natively from scratch in Metal and Swift. Build for AirVis app.
Dec 2025 · twitter.com
- 21
- 22EE
I wanted Apple Vision Pros, but I don’t have $3,500 in my back pocket. So I made Apple Vision Pros at home. This was just a fun little project I made. Currently, the website doesn't work on screens less than 1200x728 (Sorry mobile users!) It also might struggle on lower end devices. For best results, have a webcam pointing right at you. I tested my website with a MacBook camera. Any comments, questions, or suggestions are greatly appreciated! blog: https://blog.andykhau.com/blog/eyesite check it out: https://eyesite.andykhau.com/ github:…
2025 · blog.andykhau.com
- 23IV
This is a GPU "software" raytracer (i.e. using manual ray-scene intersections and not RTX) written using the WebGPU API that renders glTF scenes. It supports many materials, textures, material & normal mapping, and heavily relies on multiple importance sampling to speed up convergence.
2024 · github.com
- 24MA
Hello HN! I’m excited to share this open-source community mashup showing the power and possibility of combining 3D Gaussian splat scans with traditional mesh-based 3D tiles maps in the browser. As you've probably seen on HN a bunch lately, Gaussian splats are a new method to allow custom 3D scans of scenes and objects [1] and Google Maps 3D Tiles API are the same 3D buildings and street views your familiar with in Google Earth or Google Maps, and recently they’ve been made available for inclusion in web apps. Combining splats + 3d map mixes highly detailed real-world custom micro-scans with…
2024 · maps-and-splats.glitch.me
Ranked by how close each launch is in meaning, then by votes. Refine with a description →