Instructions to use Shiftedx/ornith-1.5-9b-affine4-vision-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shiftedx/ornith-1.5-9b-affine4-vision-mlx with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("Shiftedx/ornith-1.5-9b-affine4-vision-mlx")
config = load_config("Shiftedx/ornith-1.5-9b-affine4-vision-mlx")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use Shiftedx/ornith-1.5-9b-affine4-vision-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Shiftedx/ornith-1.5-9b-affine4-vision-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Shiftedx/ornith-1.5-9b-affine4-vision-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use Shiftedx/ornith-1.5-9b-affine4-vision-mlx with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Shiftedx/ornith-1.5-9b-affine4-vision-mlx"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Shiftedx/ornith-1.5-9b-affine4-vision-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Shiftedx/ornith-1.5-9b-affine4-vision-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Shiftedx/ornith-1.5-9b-affine4-vision-mlx"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Shiftedx/ornith-1.5-9b-affine4-vision-mlx" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

ornith-1.5-9b-affine4-vision-mlx

Compact affine 4-bit MLX quant with the parent model's BF16 vision tower. Built from Ornith-1.5-9B revision 98db59b for Apple Silicon.

Format

Size: 6.53 GB
Language trunk: 250 affine-4 modules, including recurrent inputs
Vision: 333 same-parent BF16 tensors
Context metadata: 262,144 tokens
Runtime: autoregressive MLX-LM/MLX-VLM
Native MTP: unavailable; the upstream checkpoint contains no mtp.* tensors

Exact precision and conversion records are included in BUILD_RECIPE.json and conversion_receipt.json. Immutable weight revision: 514b626.

Usage

python -m mlx_vlm.generate \
  --model Shiftedx/ornith-1.5-9b-affine4-vision-mlx \
  --image image.jpg \
  --prompt "Describe this image." \
  --max-tokens 256

Qualification

ShiftedX Bench v0.3.0 commit 3bbb0bfa01e33503163cb34ef52b4d507e456265, Apple M4 Max / 64 GiB, thinking enabled, medium reasoning, temperature 1, top-p 0.95, top-k 20, KV cache off:

Lane	Result	Mean decode	Peak active memory
Quality	6/10	67.7 tok/s	5.60 GB
Long context	3/15	61.8 tok/s	5.60 GB
Tools	6/6	62.4 tok/s	6.70 GB
Agentic	1/2	—	—
Vision, native MLX-VLM	4/4 strict	—	—

Text lanes used MTPLX 2.7.1 in stock autoregressive mode. Vision used native MLX-VLM because MTPLX AR rejects image content. Structural loading and deterministic text/vision smokes passed. Quantization can change behavior; see the parent model card for intended use and license details.

Downloads last month: 83

Safetensors

Model size

2B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for Shiftedx/ornith-1.5-9b-affine4-vision-mlx

Base model

ornith-ai/Ornith-1.5-9B

Quantized

(38)

this model

Collection including Shiftedx/ornith-1.5-9b-affine4-vision-mlx

Ornith 1.5 9B Apple Silicon MLX Vision Quants

Collection

Five vision-preserving Ornith 1.5 9B MLX quants for Apple Silicon: standard MXFP4/MXFP8, affine controls, and an Attention8 hybrid. • 5 items • Updated 2 days ago