Instructions to use OsaurusAI/Ornith-1.5-9B-MXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/Ornith-1.5-9B-MXFP8 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("OsaurusAI/Ornith-1.5-9B-MXFP8")
config = load_config("OsaurusAI/Ornith-1.5-9B-MXFP8")

# 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 OsaurusAI/Ornith-1.5-9B-MXFP8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Ornith-1.5-9B-MXFP8"

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": "OsaurusAI/Ornith-1.5-9B-MXFP8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use OsaurusAI/Ornith-1.5-9B-MXFP8 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 "OsaurusAI/Ornith-1.5-9B-MXFP8"

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 OsaurusAI/Ornith-1.5-9B-MXFP8

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OsaurusAI/Ornith-1.5-9B-MXFP8 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Ornith-1.5-9B-MXFP8"

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 "OsaurusAI/Ornith-1.5-9B-MXFP8" \
  --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"

OsaurusAI/Ornith-1.5-9B-MXFP8

MXFP8 MLX bundle of ornith-ai/Ornith-1.5-9B — 8-bit reference bundle; the quality baseline the JANG tiers are measured against.

Ornith 1.5 is an agentic coding / reasoning VLM built on a hybrid gated-delta linear attention + full attention backbone (3:1), with a 27-layer vision tower and native video support.

Bundle

Field	Value
Source	`ornith-ai/Ornith-1.5-9B`
Architecture	`qwen3_5` / `Qwen3_5ForConditionalGeneration`
Size on disk	9.45 GiB
Layers	32
Hidden size	4096
Context	262,144
Shards	10
Quantization	uniform 8-bit mxfp8, group size 32

How it was quantized

Uniform 8-bit affine (group size 32). This is the reference bundle: the JANG tiers below are measured against it.

Modalities

Modality	Status
Text	supported
Vision	supported — 333 vision-tower tensors, `preprocessor_config.json` + `processor_config.json` ride with the bundle
Video	supported — `video_preprocessor_config.json` present; verified end-to-end
Audio	not supported. The tokenizer defines `<

Reasoning

Reasoning is ON by default — the no-kwarg generation prompt is byte-identical to enable_thinking=True and ends <|im_start|>assistant\n<think>\n.

It is toggleable, but note how: enable_thinking=False does not remove the think block, it prefills an empty closed one (<think>\n\n</think>\n\n). A parser testing merely for the presence of a <think> block will find one in both modes — test whether it has content.

There are no reasoning_effort tiers on this model family (unlike Qwen3.8). History <think> blocks are preserved unconditionally. Reasoning parser: qwen3; tool parser: qwen3_coder.

Sampling

Both presets from the vendor card are stamped into jang_config.json, and the coding preset is also written to generation_config.json so the two files agree.

Ornith 1.5 is an agentic coding model (SWE-bench Verified 79, Terminal-Bench 2.1 67.8), so this bundle defaults to the coding preset. Upstream's own generation_config.json ships the general numbers (temp 1.0, presence 1.5) — use sampling_modes.general if you want parity with the vLLM/Transformers defaults.

Preset	temp	top_p	top_k	min_p	presence	repetition
general	1.0	0.95	20	0.0	1.5	1.0
coding (default)	0.6	0.95	20	0.0	0.0	1.0

Stop tokens: [248046, 248044] (<|im_end|>, <|endoftext|>).

Speculative decoding (MTP)

The 9B checkpoint declares mtp_num_hidden_layers: 1 but ships no mtp.* weights, so there is no MTP head to preserve (mtp_mode: metadata_only_missing_weights). Native MTP exists on the 35B-A3B member of this family.

Credits

JANG quantization by Jinho Jang — eric@osaurus.ai

Base model: ornith-ai/Ornith-1.5-9B by Ornith AI.

Downloads last month: 295

Safetensors

Model size

3B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized

Model tree for OsaurusAI/Ornith-1.5-9B-MXFP8

Base model

ornith-ai/Ornith-1.5-9B

Finetuned

(7)

this model