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

Libraries

How to use deepreinforce-ai/Ornith-1.0-35B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="deepreinforce-ai/Ornith-1.0-35B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("deepreinforce-ai/Ornith-1.0-35B-GGUF", dtype="auto")

llama-cpp-python

How to use deepreinforce-ai/Ornith-1.0-35B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="deepreinforce-ai/Ornith-1.0-35B-GGUF",
	filename="ornith-1.0-35b-Q4_K_M.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 deepreinforce-ai/Ornith-1.0-35B-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 deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf deepreinforce-ai/Ornith-1.0-35B-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 deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf deepreinforce-ai/Ornith-1.0-35B-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 deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf deepreinforce-ai/Ornith-1.0-35B-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 deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use deepreinforce-ai/Ornith-1.0-35B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepreinforce-ai/Ornith-1.0-35B-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": "deepreinforce-ai/Ornith-1.0-35B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M

SGLang

How to use deepreinforce-ai/Ornith-1.0-35B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "deepreinforce-ai/Ornith-1.0-35B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepreinforce-ai/Ornith-1.0-35B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "deepreinforce-ai/Ornith-1.0-35B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepreinforce-ai/Ornith-1.0-35B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use deepreinforce-ai/Ornith-1.0-35B-GGUF with Ollama:
```
ollama run hf.co/deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M
```

Unsloth Studio

How to use deepreinforce-ai/Ornith-1.0-35B-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 deepreinforce-ai/Ornith-1.0-35B-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 deepreinforce-ai/Ornith-1.0-35B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use deepreinforce-ai/Ornith-1.0-35B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deepreinforce-ai/Ornith-1.0-35B-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": "deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use deepreinforce-ai/Ornith-1.0-35B-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 deepreinforce-ai/Ornith-1.0-35B-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 deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use deepreinforce-ai/Ornith-1.0-35B-GGUF with Docker Model Runner:
```
docker model run hf.co/deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M
```

Lemonade

How to use deepreinforce-ai/Ornith-1.0-35B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deepreinforce-ai/Ornith-1.0-35B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Ornith-1.0-35B-GGUF-Q4_K_M

List all available models

lemonade list

Aider Polyglot Benchmark Results (C++ & Python) — Q4 through Q8

#23

by YukiTomita-CC - opened 3 days ago

Discussion

YukiTomita-CC

3 days ago

Ran Ornith-1.0-35B-GGUF across four quantization levels for comparison with other models I've tested under the same conditions. Only C++ and Python subsets were measured (not the full 6-language suite).

Ornith-1.0-35B-GGUF

Quant	Language	pass@1	pass@2
Q4_K_M	C++	34.6	73.1
Q4_K_M	Python	26.5	58.8
Q5_K_M	C++	30.8	69.2
Q5_K_M	Python	35.3	61.8
Q6_K	C++	26.9	80.8
Q6_K	Python	32.4	61.8
Q8_0	C++	34.6	76.9
Q8_0	Python	38.2	64.7

Qwen & Gemma

Model	Quant	Language	pass@1	pass@2
Qwen3.6-27B	UD-Q4_K_XL	C++	30.8	84.6
Qwen3.6-27B	UD-Q4_K_XL	Python	38.2	70.6
Qwen3.6-35B-A3B	UD-Q4_K_XL	C++	23.1	69.2
Qwen3.6-35B-A3B	UD-Q4_K_XL	Python	41.2	58.8
Gemma4-31B	UD-Q4_K_XL	C++	7.7	50.0
Gemma4-31B	UD-Q4_K_XL	Python	14.7	64.7

Setup: llama.cpp b3fed31 (CUDA), Aider 5dc9490 (edit-format: whole)

llama-server \
  --model ornith-1.0-35b-Q4_K_M.gguf
  --temp 0.6 \
  --top-p 0.95 \
  --top-k 20 \
  --min-p 0.0 \
  --presence-penalty 0.0 \
  --repeat-penalty 1.0 \
  --chat-template-kwargs '{"preserve_thinking": true}' \
  -c 131072 \
  -ngl 99 \
  --jinja \
  -fa on \
  --parallel 4 \
  --reasoning on

I omitted --chat-template-file. For agentic setups with tool calls, adding --chat-template-file chat_template.jinja (froggeric/Qwen-Fixed-Chat-Templates) appears to help with stability up to moderate context lengths → discussion #6

For comparison with other models (including API-based ones) across C++, Python, diff, and whole formats, I maintain a public benchmark repo: https://github.com/YukiTomita-CC/my-aider-bench

Launch80

2 days ago

Only Q4 for Qwen and Gemma? That doesn't seem like a good comparison

YukiTomita-CC

1 day ago

Certainly, testing Qwen and Gemma only at Q4 wasn't a fair comparison, since my local hardware constraints meant I could only run them at that quant level.
My main goals were

to compare Ornith-1.0 against Qwen/Gemma at Q4
to see how Ornith-1.0's results change from Q4 through Q8

Should've made both of those clearer in the original post. Thanks for the callout.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment