Instructions to use srv-sngh/Ornith-9B-mlx-nvfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use srv-sngh/Ornith-9B-mlx-nvfp4 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("srv-sngh/Ornith-9B-mlx-nvfp4")
config = load_config("srv-sngh/Ornith-9B-mlx-nvfp4")

# 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 srv-sngh/Ornith-9B-mlx-nvfp4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "srv-sngh/Ornith-9B-mlx-nvfp4"

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": "srv-sngh/Ornith-9B-mlx-nvfp4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use srv-sngh/Ornith-9B-mlx-nvfp4 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 "srv-sngh/Ornith-9B-mlx-nvfp4"

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 srv-sngh/Ornith-9B-mlx-nvfp4

Run Hermes

hermes

OpenClaw new

How to use srv-sngh/Ornith-9B-mlx-nvfp4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "srv-sngh/Ornith-9B-mlx-nvfp4"

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 "srv-sngh/Ornith-9B-mlx-nvfp4" \
  --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-1.0-9B - MLX nvfp4 (complete VLM, Krill-native)

A mixed-precision nvfp4 (group 16) quantization of deepreinforce-ai/Ornith-1.0-9B, a Qwen3.5-class hybrid vision-language model.

Original model and weights by deepreinforce-ai (Ornith-1.0-9B). Full credit to them; this repo only re-quantizes their model.

Why this build

👁️ Complete vision-language model, the vision tower is included. Many community MLX/quantized Ornith builds are text-only (vision stripped). This one keeps the full VLM, so it does image + text, not just text.
🎯 nvfp4 mixed precision. The decoder is nvfp4 at group size 16, with down_proj and o_proj protected at 8-bit and the vision tower kept at higher precision. Smaller and faster than int4 at comparable quality.
⚡ Native Krill runtime (Krill v0.14.1). Runs as a native Swift + MLX model on Apple Silicon. Krill ships a from-scratch native runtime for Ornith's hybrid GatedDeltaNet (SSM) + attention decoder, not just an mlx_vlm passthrough.
✅ Parity-verified. Text decoder matches mlx_vlm token-for-token on the reference checkpoint.
💻 Fits a 24 GB Apple-silicon box at ~6.4 GB.

Run in Krill (recommended)

# install Krill
brew tap srvsngh99/krill && brew install krill
# or:
curl -fsSL https://raw.githubusercontent.com/srvsngh99/Krill/main/install.sh | sh

# run Ornith nvfp4 (pulls this repo)
krill run ornith-9b-nvfp4 "Give three tips for staying focused while studying."

# keep Krill up to date
krill update

Run with mlx_vlm (text + vision)

pip install -U mlx-vlm
python -m mlx_vlm generate --model srv-sngh/Ornith-9B-mlx-nvfp4 \
  --prompt "Describe this image." --image path/to/image.jpg --max-tokens 200

About Ornith-1.0-9B

A Qwen3.5-class hybrid VLM: the text decoder is a Qwen3-Next-style stack interleaving GatedDeltaNet linear-attention (SSM) layers with full softmax-attention every fourth layer, plus a vision tower. Full credit to the original creators, deepreinforce-ai.

Quantization

field	value
format	MLX nvfp4 (mixed precision)
group size	16
protected	`down_proj`, `o_proj` @ 8-bit; vision tower at higher precision
size	~6.4 GB
contents	complete VLM (text decoder + vision tower)

In Krill, the text decoder runs natively; the vision tower currently runs via mlx_vlm (native vision is a follow-up).

License

MIT, matching the base model deepreinforce-ai/Ornith-1.0-9B.

Downloads last month: 179

Safetensors

Model size

3B params

Tensor type

U32

F16

MLX

Hardware compatibility

4-bit

Model tree for srv-sngh/Ornith-9B-mlx-nvfp4

Base model

deepreinforce-ai/Ornith-1.0-9B

Quantized

(59)

this model