Hacker News: shivampkumar

New comment by shivampkumar in "Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon"

shivampkumar — Mon, 20 Apr 2026 08:33:02 +0000

that makes so much sense...I am exploring if I can find someone who has done this well...If not I'll try to do it myself.

New comment by shivampkumar in "Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon"

shivampkumar — Mon, 20 Apr 2026 04:45:46 +0000

The model needed about 15GB at peak during generation - the 4B model loads multiple sub-models (1.3B each for shape and texture flow). 8GB won't be enough, but both 24GB and 32GB both should be fine.

New comment by shivampkumar in "Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon"

shivampkumar — Mon, 20 Apr 2026 03:57:40 +0000

added! will add more, maybe even a GIF

New comment by shivampkumar in "Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon"

shivampkumar — Mon, 20 Apr 2026 03:37:06 +0000

i was able to get it in 3.5 mins from a single image on my 24gb m4 pro macbook

I'm still working on this to try to replicate nvdiffrast better. Found an open source port, might look it tonight

New comment by shivampkumar in "Show HN: TRELLIS.2 image-to-3D running on Mac Silicon – no Nvidia GPU needed"

shivampkumar — Mon, 20 Apr 2026 03:32:15 +0000

thanks!

New comment by shivampkumar in "Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon"

shivampkumar — Mon, 20 Apr 2026 03:27:53 +0000

I mean I can see that it's niche. Did not expect so many upvotes, but ig it's less niche than I tought

If you're not working with 3D on Apple Silicon this isn't relevant to you. For the subset of people who are, running this 4B parameter 3D generation model locally on a Mac was previously blocked by hard CUDA dependencies with no workaround.

New comment by shivampkumar in "Show HN: TRELLIS.2 image-to-3D running on Mac Silicon – no Nvidia GPU needed"

shivampkumar — Mon, 20 Apr 2026 03:26:17 +0000

I thought it was cool and then I found the open issue mentioned above, that convinced me its def something more people want.

It IS significantly slower, about 3.5 minutes on my MacBook vs seconds on an H100. That's partly the pure-PyTorch backend overhead and partly just the hardware difference.

For my use case the tradeoff works -- iterate locally without paying for cloud GPUs or waiting in queues.

New comment by shivampkumar in "Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon"

shivampkumar — Mon, 20 Apr 2026 03:22:33 +0000

IMO TRELLIS.2 is slightly different case from the HF models scenario. It depends on five compiled CUDA-only extensions -- flex_gemm for sparse convolution, flash_attn, o_voxel for CUDA hashmap ops, cumesh for mesh processing, and nvdiffrast for differentiable rasterization. These aren't PyTorch ops that fall back to MPS -- they're custom C++/CUDA kernels. The upstream setup.sh literally exits with "No supported GPU found" if nvidia-smi isn't present. The only reason I picked this up because I thought it was cool and no one was working on this open issue for Silicon back then (github.com/microsoft/TRELLIS.2/issues/74) requesting non-CUDA support.

New comment by shivampkumar in "Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon"

shivampkumar — Mon, 20 Apr 2026 03:05:47 +0000

You're right, thanks for flagging this, let me run something and push images

New comment by shivampkumar in "Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon"

shivampkumar — Mon, 20 Apr 2026 03:03:56 +0000

Hey, thanks for sharing this. I'm sure TRELLIS.2 definitely has room to improve, especially on texturing.

From what I've seen personally, and community benchmarks, it does fair on geometry and visual fidelity among open-source options, but I agree it's not perfect for every use case.

Meshy is solid, I used it to print my girlfriend a mini 3d model of her on her birthday last year!

Though worth noting it's a paid service, and free tier has usage limitations while TRELLIS.2 is MIT licensed with unlimited local generation. Different tradeoffs for different workflows. Hopefully the open-source side keeps improving.

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

shivampkumar — Mon, 20 Apr 2026 00:07:16 +0000

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

Comments URL: https://news.ycombinator.com/item?id=47828896

Points: 192

# Comments: 34