Alternatives
Products that do what Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon does
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…
- 1OS
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
- 2
- 3AS
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…
May 2026 · github.com
- 4
- 5I3
2017 · github.com
- 6
- 7
- 8CP
2018 · dust3d.org
- 9
- 101F
2018 · github.com
- 11
- 12I4
It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https://ideogram.ai/blog/ideogram-4.0/ We will be happy to answer any questions :)
Jun 2026 · github.com
- 13PO
Our company Vertex.AI has been working on this for a while but this is the first public release. We're starting with using PlaidML to bring OpenCL support to Keras and more frameworks, platforms, etc are coming. Yes, this means you can use use your AMD GPU for deep learning dev. Sorry, no Mac or Windows support yet although the brave can try building from source (it should work). http://vertex.ai/blog/announcing-plaidml https://github.com/plaidml/plaidml
2017
- 14IR
Jun 2026 · github.com
- 15IC
This is an upgrade of a tool I created 15 years ago in Python to learn OOP and solve some inadequacies in the HDR stacking tools I could find at the time. The problem was, none of them were really "batch friendly". None of them properly preserved the metadata I wanted them to stuff into the output file. There were probably some other reasons also, I just can't remember them now. It got the job done, but was very slow. Python was what I knew at the time and even with NumPy, I was limited in the speed I could squeeze out of it. (I also made some very specific, conscious, architectural choices…
Jun 2026 · github.com
- 16
- 17
- 18CI
2013 · exocortex.com
- 19CN
2019 · github.com
- 20PA
2021 · github.com
- 21RG
I wanted to know how fast a 26B mixture-of-experts model could run on a desktop CPU with no GPU. Got ~40 tok/s single-stream (lossless) and ~124 batched. The surprising part was the byte budget: for this model you compress the output head (32% of per-token bytes), not the experts (16%). The writeup has the bandwidth roofline and the dead-ends; the repo has the reproducible recipe. Happy to answer questions. Repo: https://github.com/arun-prasath2005/gemma4-cpu-moe
Jun 2026 · apeg.dev
- 22IM
I made my first macOS utility app that ships with a bundled Gemma 4 model, specifically the Gemma E4B one. It made my app DMG have 5.3 GB in size, but I think it is a small size for the power that this free local model can provide. It runs fine on CPU, but can also run on Apple Silicon GPU, although I did not notice any performance improvements with GPU (tested on a M5 chip). I think these local lightweight and multimodal models will open multiple possibilities for new software tools where privacy is essential.
May 2026 · snapname.app
- 23SP
I was recently playing with Apple's CoreML and had several painful observations on tooling. It's not enough for a long read but should be for an HN post. In short, you can take a simple BERT-like encoder model in PyTorch, convert it into an f32 CoreML checkpoint, and run it on CPU or GPU, but not NPU. Let's unpack this. Having a simple and extensible format to exchange common ANN architectures is a big issue for anyone who uses more than one framework or programming language to run the same model. ONNX is the closest we have to that standard, but it's hard to call anything Protobuf-related…
2024 · github.com
- 24L2
2022 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →