Show HN: Apple's Sharp Running in the Browser via ONNX Runtime Web

Re:Show HN: Apple's Sharp Running in the Browser via ONNX Ru... by herpdyderp on Sunday May 03, 2026 @09:22AM (#47996708)

Loading the model crashes my browser tab from memory usage :/

[ Parent | on HN ]

Re:Show HN: Apple's Sharp Running in the Browser via ONNX Ru... by bring-shrubbery on Sunday May 03, 2026 @01:26PM (#47999247)

Yeah, I think you need at least 8gb ram unfortunately, but I tested it only on a 32gb M2, so 8gb might also not be enough.

I might create a compressed version of the model, that would work on low-ram machines.

[ Parent | on HN ]

Re:Show HN: Apple's Sharp Running in the Browser via ONNX Ru... by kodablah on Sunday May 03, 2026 @01:56PM (#47999560)

I've worked around lower RAM machines with ONNX web models by first separating .onnx from .onnx_data, and second having scripts that split up the "layers" and shards the run (e.g. https://huggingface.co/cretz/Z-Image-Turbo-ONNX-sharded). Then you can have the runtime only run one at a time. I don't understand the details too deep, but Claude is good at writing scripts to shard onnx protos.

[ Parent | on HN ]

Re:Show HN: Apple's Sharp Running in the Browser via ONNX Ru... by anentropic on Sunday May 03, 2026 @02:24PM (#47999843)

It froze up my computer, had to hard-boot lol

(16MB M1 Macbook, Chrome)

[ Parent | on HN ]