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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use audreyt/Ornith-1.5-9B-DFlash-GGUF 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 audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

Use Docker

docker model run hf.co/audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use audreyt/Ornith-1.5-9B-DFlash-GGUF with Ollama:
```
ollama run hf.co/audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M
```

Unsloth Studio

How to use audreyt/Ornith-1.5-9B-DFlash-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for audreyt/Ornith-1.5-9B-DFlash-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for audreyt/Ornith-1.5-9B-DFlash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for audreyt/Ornith-1.5-9B-DFlash-GGUF to start chatting

How to use audreyt/Ornith-1.5-9B-DFlash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use audreyt/Ornith-1.5-9B-DFlash-GGUF with Docker Model Runner:
```
docker model run hf.co/audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M
```

Lemonade

How to use audreyt/Ornith-1.5-9B-DFlash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ornith-1.5-9B-DFlash-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use audreyt/Ornith-1.5-9B-DFlash-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

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 audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use audreyt/Ornith-1.5-9B-DFlash-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M

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 "audreyt/Ornith-1.5-9B-DFlash-GGUF:Q4_K_M" \
  --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 DFlash GGUF

A target-specific classic DFlash draft for ornith-ai/Ornith-1.5-9B, initialized from z-lab/Qwen3.5-9B-DFlash and distilled against Ornith 1.5 target features.

This is not a standalone language model. Pair it with the Ornith 1.5 9B target in a runtime that supports classic DFlash speculative decoding.

File

File	Quantization	SHA-256
`ornith1.5-9b-dflash-bf16-projection-Q4_K_M.gguf`	Q4_K_M	`76ed0c5d3c401d9d518b2fd9b8468b0ccdd7f07c51f0108234e4a6eadbc511f2`

Training

The six-layer Qwen3.5 DFlash backbone was retained. Projection-specific distillation unfroze fc and hidden_norm, while the remaining draft layers stayed frozen.

Target: ornith-ai/Ornith-1.5-9B
Initialization: z-lab/Qwen3.5-9B-DFlash
Corpus: 144 target-generated Alpaca prompts and responses
Target features: cached from the BF16 Ornith target
Training: 4,096 projection-only optimization steps
Objective: position-weighted block cross-entropy following the DFlash objective
Evaluation mean accepted length: 2.50 before → 2.77 after distillation
Export: GGUF Q4_K_M using current llama.cpp tooling

The training pipeline is included in this repository as dflash_distill_mlx.py.

DS4 usage

./ds4 \
  -m Ornith-1.5-9B-Q4_K_M.gguf \
  --dflash ornith1.5-9b-dflash-bf16-projection-Q4_K_M.gguf \
  -p "Count from 1 to 100."

DS4's adaptive scheduler is enabled by default. It probes draft yield, increases the speculative block only when profitable, and falls back to target-only decoding on low-yield text. Set DS4_DFLASH_ADAPTIVE=0 to disable adaptation.

Measured results

Apple M4, Ornith 1.5 9B Q4_K_M target, greedy decoding:

Workload	Target only	Adaptive DFlash	Acceptance
128-token counting conversation	16.24 tok/s	18.97 tok/s	109/110
64-token literary text	15.62 tok/s	13.85 tok/s	Scheduler rejected the probe and fell back

The counting workload improved by 16.8%. Low-yield text does not benefit; its short benchmark includes the one-time probe cost, after which DS4 stays target-only.

Greedy target-only and speculative outputs were byte-identical for a normal chat prompt and a 128-token counting conversation.

Limitations

Target-specific: acceptance may be substantially lower with base Qwen3.5 or another fine-tune.
Throughput depends on runtime kernels, hardware, prompt distribution, and accepted length.
The reported exactness checks cover greedy decoding in DS4. Other runtimes and sampling modes were not qualified here.
This repository contains only the draft. Download the target separately from ornith-ai/Ornith-1.5-9B-GGUF.

Acknowledgements and licenses

The draft initialization is from Z-Lab's Apache-2.0 Qwen3.5 DFlash release. Ornith 1.5 is released under MIT. See the upstream repositories for their respective license texts and model documentation.

Downloads last month: 301

GGUF

Model size

1B params

Architecture

dflash

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for audreyt/Ornith-1.5-9B-DFlash-GGUF

Base model

ornith-ai/Ornith-1.5-9B

Quantized

(49)

this model