Show HN: TRELLIS.2 image-to-3D running on Mac Silicon

Re:Show HN: TRELLIS.2 image-to-3D running on Mac Silicon – n... by post-it on Monday April 20, 2026 @12:04AM (#47830291)

How much RAM does this use? Only sitting on 8 GB right now, I'm trying to figure out if I should buy 24 GB when it's time for a replacement or spring for 32.

[ Parent | on HN ]

Re:Show HN: TRELLIS.2 image-to-3D running on Mac Silicon – n... by shivampkumar on Monday April 20, 2026 @12:45AM (#47830491)

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.

[ Parent | on HN ]

Re:Show HN: TRELLIS.2 image-to-3D running on Mac Silicon – n... by post-it on Monday April 20, 2026 @01:07AM (#47830583)

Thanks! Could it conceivably load the sub-models in series rather than parallel? 8 still won't be enough but I wonder if those with 16 could eke something out.

[ Parent | on HN ]

Re:Show HN: TRELLIS.2 image-to-3D running on Mac Silicon – n... by shivampkumar on Thursday April 23, 2026 @08:45PM (#47884155)

In theory yes - the pipeline already does this to some extent with its low_vram mode, offloading models to CPU between stages. The challenge at 16GB is that even a single 1.3B sub-model at fp32 plus activations can push past what's available after macOS takes its share. Someone on an M1 iMac with 16GB did get geometry generation working tho (issue #5 on the repo), so 16GB is probably possible. 24GB gives comfortable headroom though.

[ Parent | on HN ]