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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TeamIDE/Ornith-1.5-9B-Pantheon-TT with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0
# Run inference directly in the terminal:
llama cli -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0
# Run inference directly in the terminal:
llama cli -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

Use Docker

docker model run hf.co/TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use TeamIDE/Ornith-1.5-9B-Pantheon-TT with Ollama:
```
ollama run hf.co/TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0
```
Unsloth Desktop

How to use TeamIDE/Ornith-1.5-9B-Pantheon-TT with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TeamIDE/Ornith-1.5-9B-Pantheon-TT with Docker Model Runner:
```
docker model run hf.co/TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0
```

Lemonade

How to use TeamIDE/Ornith-1.5-9B-Pantheon-TT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

Run and chat with the model

lemonade run user.Ornith-1.5-9B-Pantheon-TT-Q8_0

List all available models

lemonade list

Hermes Agent

How to use TeamIDE/Ornith-1.5-9B-Pantheon-TT with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

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 TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TeamIDE/Ornith-1.5-9B-Pantheon-TT with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0

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 "TeamIDE/Ornith-1.5-9B-Pantheon-TT:Q8_0" \
  --custom-provider-id llama-cpp \
  --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 — Pantheon Tenstorrent build (Q8_0)

The files Pantheon Local installs for Tenstorrent Blackhole p150 boxes.

Ornith-1.5-9B-Q8_0.gguf — Q8_0 GGUF of ornith-ai/Ornith-1.5-9B (from ornith-ai/Ornith-1.5-9B-GGUF), unmodified.
Ornith-1.5-9B-Q8_0.bfp8.fttw — the same weights converted by Pantheon/Foundry into the card's Bfp8 tile format, so the box loads it directly with no conversion step. Modified (format conversion) from the GGUF above.
Ornith-1.5-9B-Q8_0.bfp8.mtp.fttw — a multi-token-prediction draft head for Pantheon's speculative decoding, fine-tuned by TeamIDE (ft_all2) from the model's MTP head. Modified.

License: MIT, as stated on the original model card (https://huggingface.co/ornith-ai/Ornith-1.5-9B). The upstream repositories ship no LICENSE file and name no copyright holder; the MIT terms apply to these files, including our modified ones. Ornith is built on Qwen3.5 (Apache-2.0, © the Qwen team).

Measured on Pantheon, one p150 (greedy, MTP on): decode 40.8 tok/s at 7.4k context, 37.9 at 14.6k. Pantheon: https://git.teamide.dev/David/Pantheon

Downloads last month: 26

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TeamIDE/Ornith-1.5-9B-Pantheon-TT

Base model

ornith-ai/Ornith-1.5-9B

Quantized

(100)

this model