LookUpMark/Ornith-1.5-35B-A3B-oQ4e-mtp

Ornith-1.5-35B-A3B · MLX 4-bit (oQ4e) + MTP

MLX quantization of ornith-ai/Ornith-1.5-35B-A3B — a Mixture-of-Experts model with ~3B active parameters — in 4-bit (oQ4e) with Multi-Token Prediction (MTP, speculative depth 3), built to run on Apple Silicon via a local oMLX server.

Status: weights upload in progress — this card ships first; file list and hashes will land with the weights.

Credits

All credit for the base model goes to the Ornith team (ornith-ai):

• Base model: ornith-ai/Ornith-1.5-35B-A3B (MIT — see LICENSE), which extends Ornith-1.0 (built on Qwen3.5 and Gemma4) via an end-to-end self-improvement loop
• Blog: deep-reinforce.com/ornith.html · ornith.ai/ornith_1_5.html

This repo is only a quantization for local Apple Silicon inference. Same MIT terms apply.

Intended use

Local inference on Apple Silicon Macs (oMLX / mlx-lm). For benchmarks and model details, see the upstream card.