mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit

Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. All OptiQ quants · Docs

OptiQ mixed-precision quant of ornith-ai/Ornith-1.5-35B-A3B, a 35B mixture-of-experts vision-language model with 3B active parameters and a bundled MTP speculation head. 24 GB on disk.

What it is

Property	Value
Base	ornith-ai/Ornith-1.5-35B-A3B (Qwen3.5-MoE, 35B total / 3B active)
Method	OptiQ mixed-precision, per-layer 4/8-bit
Bit allocation	Reused from the Ornith-1.0-35B OptiQ recipe: the architecture is identical, so the per-layer sensitivity ranking transfers directly and no per-model sweep is needed
Layer split	113 components at 4-bit, 399 at 8-bit
Group size	64
On disk	24 GB
MTP	Speculation head preserved in optiq/mtp.safetensors
Vision	bf16 vision tower kept in optiq/optiq_vision.safetensors for image input

Following the naming llama.cpp uses for its mixed quants, the "4bit" label denotes the family, not the weighted average.

Run it

The MoE arch and the MTP/vision sidecars register through OptiQ, so import optiq once before loading:

pip install "mlx-optiq>=0.4.27"

import optiq  # registers the arch + MTP/vision sidecars
from mlx_lm import load, generate

model, tok = load("mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit")
prompt = tok.apply_chat_template(
    [{"role": "user", "content": "Explain mixture-of-experts routing in two sentences."}],
    tokenize=False, add_generation_prompt=True,
)
print(generate(model, tok, prompt=prompt, max_tokens=400))

For image input plus an OpenAI- and Anthropic-compatible endpoint with mixed-precision KV cache:

optiq serve --model mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit

This is a reasoning model, so give it a generous token budget.

Links

• Project website: mlx-optiq.com
• All OptiQ quants: mlx-optiq.com/models
• Base model: ornith-ai/Ornith-1.5-35B-A3B