Instructions to use ORCA-AI/ORCA1-TURBO-EXP-0214 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ORCA-AI/ORCA1-TURBO-EXP-0214 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ORCA-AI/ORCA1-TURBO-EXP-0214",
	filename="ORCA1-TURBO-EXP-0214.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 ORCA-AI/ORCA1-TURBO-EXP-0214 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 ORCA-AI/ORCA1-TURBO-EXP-0214
# Run inference directly in the terminal:
llama cli -hf ORCA-AI/ORCA1-TURBO-EXP-0214

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ORCA-AI/ORCA1-TURBO-EXP-0214
# Run inference directly in the terminal:
llama cli -hf ORCA-AI/ORCA1-TURBO-EXP-0214

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 ORCA-AI/ORCA1-TURBO-EXP-0214
# Run inference directly in the terminal:
./llama-cli -hf ORCA-AI/ORCA1-TURBO-EXP-0214

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 ORCA-AI/ORCA1-TURBO-EXP-0214
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ORCA-AI/ORCA1-TURBO-EXP-0214

Use Docker

docker model run hf.co/ORCA-AI/ORCA1-TURBO-EXP-0214

LM Studio
Jan

vLLM

How to use ORCA-AI/ORCA1-TURBO-EXP-0214 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ORCA-AI/ORCA1-TURBO-EXP-0214"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ORCA-AI/ORCA1-TURBO-EXP-0214",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ORCA-AI/ORCA1-TURBO-EXP-0214

Ollama
How to use ORCA-AI/ORCA1-TURBO-EXP-0214 with Ollama:
```
ollama run hf.co/ORCA-AI/ORCA1-TURBO-EXP-0214
```

Unsloth Studio

How to use ORCA-AI/ORCA1-TURBO-EXP-0214 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 ORCA-AI/ORCA1-TURBO-EXP-0214 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 ORCA-AI/ORCA1-TURBO-EXP-0214 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ORCA-AI/ORCA1-TURBO-EXP-0214 to start chatting

How to use ORCA-AI/ORCA1-TURBO-EXP-0214 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ORCA-AI/ORCA1-TURBO-EXP-0214

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": "ORCA-AI/ORCA1-TURBO-EXP-0214"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ORCA-AI/ORCA1-TURBO-EXP-0214 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ORCA-AI/ORCA1-TURBO-EXP-0214

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 ORCA-AI/ORCA1-TURBO-EXP-0214

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ORCA-AI/ORCA1-TURBO-EXP-0214 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ORCA-AI/ORCA1-TURBO-EXP-0214

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 "ORCA-AI/ORCA1-TURBO-EXP-0214" \
  --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 ORCA-AI/ORCA1-TURBO-EXP-0214 with Docker Model Runner:
```
docker model run hf.co/ORCA-AI/ORCA1-TURBO-EXP-0214
```

Lemonade

How to use ORCA-AI/ORCA1-TURBO-EXP-0214 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ORCA-AI/ORCA1-TURBO-EXP-0214

Run and chat with the model

lemonade run user.ORCA1-TURBO-EXP-0214-{{QUANT_TAG}}

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

ORCA 1-TURBO-EXP-0214

ORCA 1-TURBO-EXP-0214 is an experimental, uncensored AI model developed by ORCA AI Labs.
It is optimized for speed rather than deep reasoning and is designed primarily for Czech-language conversations.
This model is uncensored, meaning it operates without artificial restrictions, making it ideal for open-ended discussions.

Features

Fast and Efficient – Optimized for low-latency inference.
Uncensored – No artificial restrictions or content filtering.
Czech Language Support – Primarily designed for Czech, with some English capability.
Lightweight – Easy to deploy and run efficiently.

Model Details

Property	Details
Type	Experimental Conversational AI
Speed	Optimized for fast responses
Intelligence	Average
Censorship	Uncensored
Best for	Open-ended conversations, quick replies
Limitations	Not suited for deep contextual understanding or logic-heavy tasks

Usage on Hugging Face

ORCA 1-TURBO-EXP-0214 is available on Hugging Face. You can load and run it using Python:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "ORCA-AI/ORCA1-TURBO-EXP-0214"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

input_text = "Jaké je hlavní město České republiky?"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Performance Overview

Metric	ORCA 1-TURBO-EXP-0214	ORCA 2-Turbo
Speed	Extremely fast	Faster than ORCA 1
Intelligence	Average	Designed for deep reasoning
Censorship	Unfiltered	Unfiltered
Language	English & 7 other	English & 7 other
Use Case	Conversational AI, quick replies	Complex tasks, in-depth responses

This model prioritizes speed over deep reasoning. It is well-suited for casual conversations in Czech but may not perform well in fact-heavy or complex discussions.

Limitations & Warnings

Uncensored – The model does not apply moderation. Use responsibly.
Not Designed for Deep Reasoning – Works well for casual interactions but may struggle with complex logic.
Experimental – Expect inconsistencies and updates over time.

Fine-Tuning & Customization

If you need to fine-tune ORCA 1-TURBO-EXP-0214, you can do so using Hugging Face's Trainer:

from transformers import Trainer, TrainingArguments

training_args = TrainingArguments(
    output_dir="./orca1-turbo-exp-0214-finetuned",
    per_device_train_batch_size=4,
    gradient_accumulation_steps=8,
    evaluation_strategy="steps",
    save_total_limit=2,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=your_dataset,
    eval_dataset=your_eval_dataset,
)

trainer.train()

Get Involved

For feedback, contributions, or inquiries, reach out to ORCA AI Labs:

Website: ORCA AI Labs
Twitter: @ORCA_AI_Labs

License

ORCA 1-TURBO-EXP-0214 is released under the ORCA Experimental License.
Full terms can be found here.

ORCA AI Labs – Advancing Open AI Research

Downloads last month: -

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants