mlx-community/Ornith-1.5-9B-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-1.5-9B-MLX, a 9B reasoning model. 7 GB on disk.
What it is
| Property | Value |
|---|---|
| Base | ornith-ai/Ornith-1.5-9B-MLX (Qwen3.5, 9B, 32 layers) |
| Method | OptiQ mixed-precision, per-layer 4/8-bit |
| Bit allocation | Reused from the Ornith-1.0-9B OptiQ recipe: same architecture and layer count, so the per-layer sensitivity ranking transfers directly and no per-model sweep is needed |
| Layer split | 116 components at 4-bit, 134 at 8-bit |
| Group size | 64 |
| On disk | 7 GB |
Following the naming llama.cpp uses for its mixed quants, the "4bit" label denotes the family, not the weighted average.
Run it
pip install "mlx-optiq>=0.4.28"
import optiq # registers the arch
from mlx_lm import load, generate
model, tok = load("mlx-community/Ornith-1.5-9B-OptiQ-4bit")
prompt = tok.apply_chat_template(
[{"role": "user", "content": "Explain mixed-precision quantization in two sentences."}],
tokenize=False, add_generation_prompt=True,
)
print(generate(model, tok, prompt=prompt, max_tokens=400))
For an OpenAI- and Anthropic-compatible endpoint with mixed-precision KV cache:
optiq serve --model mlx-community/Ornith-1.5-9B-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-1.5-9B-MLX