Idol for mlx-serve (8-bit)

speridlabs/idol repackaged for mlx-serve on Apple Silicon: one picture of an object becomes a 3D Gaussian splat, background removal included, no Python. POST /v1/3d/generations answers a GLB: a mesh of textured discs any viewer draws solid (Preview, Quick Look), or with "geometry": "splat" the KHR_gaussian_splatting points. About 40 s for 50 steps and 262,144 Gaussians on an M-series Ultra, 3.6 GB resident.

The three transformers' Linear layers are affine 8-bit, group 64, where the width allows (the rest float16); norms, embeddings and the RoPE phases are as released.
Includes everything Idol reads, so nothing else downloads: BiRefNet (background removal, as released), the DINOv3 ViT-H+/16 encoder (float16; its licence is in dinov3/LICENSE.md) and the FLUX.2 VAE encoder (vae/, from black-forest-labs/FLUX.2-klein-4B, Apache-2.0; the middle attention is 8-bit).

Licences

The Idol weights are Apache-2.0 (LICENSE, NOTICE). The bundled DINOv3 encoder is Meta's, under the DINOv3 License (dinov3/LICENSE.md), which travels with any redistribution of it.

Use

mlx-serve --model-dir <folder holding this repo>, or pick Idol in the app's 3D pane.

About mlx-serve

A native Zig server for Apple Silicon. No Python, no cloud, no Electron. One binary: chat, images, video, music, speech and 3D on MLX, behind OpenAI- and Anthropic-compatible APIs, with a signed menu-bar app.

mlxserve.com · GitHub

Converted by tests/convert_idol_weights.py in the mlx-serve repository.

Downloads last month: 33

MLX

Hardware compatibility

Quantized

Inference Providers NEW

Image-to-3D

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ddalcu/Idol-MLX-Serve-8bit

Base model

speridlabs/idol

Quantized

(2)

this model