Instructions to use wang-yang/Ornith-1.0-35B-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wang-yang/Ornith-1.0-35B-MTP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="wang-yang/Ornith-1.0-35B-MTP-GGUF",
	filename="Ornith-1.0-35B-Q6_K-MTP.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wang-yang/Ornith-1.0-35B-MTP-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 wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K
# Run inference directly in the terminal:
llama cli -hf wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

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 wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

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 wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

Use Docker

docker model run hf.co/wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

LM Studio
Jan

vLLM

How to use wang-yang/Ornith-1.0-35B-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wang-yang/Ornith-1.0-35B-MTP-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wang-yang/Ornith-1.0-35B-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

Ollama
How to use wang-yang/Ornith-1.0-35B-MTP-GGUF with Ollama:
```
ollama run hf.co/wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K
```

Unsloth Studio

How to use wang-yang/Ornith-1.0-35B-MTP-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 wang-yang/Ornith-1.0-35B-MTP-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 wang-yang/Ornith-1.0-35B-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for wang-yang/Ornith-1.0-35B-MTP-GGUF to start chatting

How to use wang-yang/Ornith-1.0-35B-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

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": "wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use wang-yang/Ornith-1.0-35B-MTP-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 wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

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 wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use wang-yang/Ornith-1.0-35B-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

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 "wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K" \
  --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"

Docker Model Runner
How to use wang-yang/Ornith-1.0-35B-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K
```

Lemonade

How to use wang-yang/Ornith-1.0-35B-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wang-yang/Ornith-1.0-35B-MTP-GGUF:Q6_K

Run and chat with the model

lemonade run user.Ornith-1.0-35B-MTP-GGUF-Q6_K

List all available models

lemonade list

Ornith-1.0-35B-MTP-GGUF / README.md

wang-yang

Ornith-1.0-35B Q6_K with grafted MTP head (1.26x via draft-mtp)

f94557b verified 21 days ago

preview code

Raw

History Blame Contribute Delete

2.29 kB

	---
	license: mit
	base_model:
	- deepreinforce-ai/Ornith-1.0-35B
	base_model_relation: quantized
	language:
	- en
	library_name: gguf
	tags:
	- gguf
	- llama.cpp
	- mtp
	- multi-token-prediction
	- speculative-decoding
	- qwen35moe
	- moe
	pipeline_tag: text-generation
	---

	# Ornith-1.0-35B-MTP-GGUF

	[Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) (qwen35moe, 35B-A3B,
	Qwen3.5 base) is a strong agentic-coding MoE that ships without MTP heads. This GGUF has an
	MTP head grafted in so it can use llama.cpp's `--spec-type draft-mtp` self-speculative
	decoding for a real speedup, with no quality change to the base weights.

	Quantization: Q6_K (body + grafted MTP head).

	## Performance (M3 Max, measured, real-prompt benchmark)

	Generation speed (tg128) on a real code-continuation prompt, sweeping draft depth:

	\| Mode \| tok/s \| Speedup \| MTP acceptance \| mean accepted len \|
	\|---\|---\|---\|---\|---\|
	\| AR (no MTP) \| 66.6 \| 1.00× \| — \| — \|
	\| draft-mtp n_max=1 \| 83.8 \| 1.26× \| 92.2% \| 1.92 \|
	\| draft-mtp n_max=2 \| 82.8 \| 1.24× \| 82.5% \| 2.65 \|
	\| draft-mtp n_max=3 \| 81.7 \| 1.23× \| 78.2% \| 3.35 \|
	\| draft-mtp n_max=4 \| 75.9 \| 1.14× \| 68.1% \| 3.72 \|

	Best: `--spec-draft-n-max 1`, ~1.26×. (Acceptance is much higher on real text than on random
	tokens — benchmark with a real prompt or you'll badly underestimate MTP.)

	## Usage (llama.cpp)

	```bash
	llama-server -m Ornith-1.0-35B-Q6_K-MTP.gguf -ngl 99 -c 32768 \
	--spec-type draft-mtp --spec-draft-n-max 1 --port 8080
	```
	Requires a llama.cpp build with `draft-mtp` speculative support.

	## Provenance & licensing

	- Base model: [deepreinforce-ai/Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) — MIT.
	- MTP head: grafted from a same-architecture (`qwen35moe`, 40 blocks) sibling that ships MTP
	heads, following the cross-model graft approach published by
	[skinnyctax/Ornith-1.0-35B-Q6_K-Frankenstein-MTP-GGUF](https://huggingface.co/skinnyctax/Ornith-1.0-35B-Q6_K-Frankenstein-MTP-GGUF) (MIT).
	The 20 MTP head tensors (`blk.40.`, incl. `nextn.`) are appended to the base GGUF and metadata
	patched (`block_count` +1, `nextn_predict_layers=1`).

	Released under MIT. No weights retrained — this is a head graft + metadata patch.