Instructions to use TurboAiLabs/turbo-ai-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TurboAiLabs/turbo-ai-7b with Transformers:

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

pipe = pipeline("text-generation", model="TurboAiLabs/turbo-ai-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TurboAiLabs/turbo-ai-7b")
model = AutoModelForCausalLM.from_pretrained("TurboAiLabs/turbo-ai-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use TurboAiLabs/turbo-ai-7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TurboAiLabs/turbo-ai-7b",
	filename="turbo-ai-7b.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 TurboAiLabs/turbo-ai-7b 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 TurboAiLabs/turbo-ai-7b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TurboAiLabs/turbo-ai-7b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TurboAiLabs/turbo-ai-7b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TurboAiLabs/turbo-ai-7b: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 TurboAiLabs/turbo-ai-7b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TurboAiLabs/turbo-ai-7b: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 TurboAiLabs/turbo-ai-7b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TurboAiLabs/turbo-ai-7b:Q4_K_M

Use Docker

docker model run hf.co/TurboAiLabs/turbo-ai-7b:Q4_K_M

LM Studio
Jan

vLLM

How to use TurboAiLabs/turbo-ai-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TurboAiLabs/turbo-ai-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TurboAiLabs/turbo-ai-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TurboAiLabs/turbo-ai-7b:Q4_K_M

SGLang

How to use TurboAiLabs/turbo-ai-7b 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 "TurboAiLabs/turbo-ai-7b" \
    --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": "TurboAiLabs/turbo-ai-7b",
		"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 "TurboAiLabs/turbo-ai-7b" \
        --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": "TurboAiLabs/turbo-ai-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use TurboAiLabs/turbo-ai-7b with Ollama:
```
ollama run hf.co/TurboAiLabs/turbo-ai-7b:Q4_K_M
```

Unsloth Studio

How to use TurboAiLabs/turbo-ai-7b 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 TurboAiLabs/turbo-ai-7b 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 TurboAiLabs/turbo-ai-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TurboAiLabs/turbo-ai-7b to start chatting

How to use TurboAiLabs/turbo-ai-7b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TurboAiLabs/turbo-ai-7b: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": "TurboAiLabs/turbo-ai-7b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TurboAiLabs/turbo-ai-7b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TurboAiLabs/turbo-ai-7b: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 TurboAiLabs/turbo-ai-7b:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use TurboAiLabs/turbo-ai-7b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TurboAiLabs/turbo-ai-7b: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 "TurboAiLabs/turbo-ai-7b: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"

Docker Model Runner
How to use TurboAiLabs/turbo-ai-7b with Docker Model Runner:
```
docker model run hf.co/TurboAiLabs/turbo-ai-7b:Q4_K_M
```

Lemonade

How to use TurboAiLabs/turbo-ai-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TurboAiLabs/turbo-ai-7b:Q4_K_M

Run and chat with the model

lemonade run user.turbo-ai-7b-Q4_K_M

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Turbo AI 7B — Advanced Local Email Intelligence ⚡️

At TurboMail, we believe your personal data—especially your emails—should never leave your device.

Turbo AI 7B is the advanced language model from TurboAI Labs, designed for high-quality private email assistance while running locally or within self-hosted environments.

Compared to Turbo AI 1.5B, Turbo AI 7B delivers stronger reasoning, better instruction following, more natural writing, and improved understanding of long email conversations.

Turbo AI 7B powers the next generation of local-first AI productivity inside TurboMail.

Why Turbo AI?

Most AI email assistants rely on cloud inference, meaning private email conversations may be transmitted to external servers.

Turbo AI is built around a different philosophy:

Private AI that works where your data lives.

Turbo AI enables organizations and individuals to run powerful AI directly on their own hardware, improving privacy, responsiveness, and control.

Key Benefits

Advanced Email Understanding

Produces higher-quality summaries, reply drafts, classifications, and action-item extraction than smaller edge models.

Privacy First

Email conversations can remain entirely on the user's device or private infrastructure.

Long Context Understanding

Handles lengthy email threads with improved consistency and context retention.

Professional Writing

Generates polished, natural business communication suitable for professional workflows.

Flexible Deployment

Supports local desktops, workstations, enterprise servers, and private AI environments.

Built for Productivity

Optimized for real-world inbox workflows instead of general-purpose conversation.

Model Details

Field	Value
Model Name	Turbo AI 7B
Organization	TurboAI Labs
Product	TurboMail
Model Type	Large local language model
Architecture	Transformer
Format	Safetensors
Primary Use Case	Advanced local email productivity
Inference Target	High-end desktops, workstations, enterprise servers
Core Focus	Email summarization, drafting, task extraction, intent parsing, inbox productivity

Intended Use Cases

Turbo AI 7B is designed for:

Email summarization
Professional reply drafting
Intent classification
Task extraction
Inbox triage
Follow-up detection
Long conversation understanding
Enterprise productivity
Private AI assistants
Local-first applications

Example workflows include:

Summarizing lengthy email chains
Writing professional responses
Extracting action items
Detecting deadlines and meetings
Identifying follow-ups
Understanding customer conversations
Assisting with internal communication
Managing enterprise inboxes privately

Example Prompts

Email Summarization

Summarize this email in 3 bullet points:

Hi Sam,

We'd like to move tomorrow's onboarding meeting to 3 PM.
Please review the attached onboarding documents beforehand and send any questions you have.
We'll also discuss sprint planning and project milestones.

Draft Reply

Write a professional response confirming attendance and thanking the sender.

Task Extraction

Extract all action items, deadlines, and responsible people from this email.

Intent Classification

Determine whether this email is:

- Information
- Request
- Meeting
- Follow-up
- Urgent
- Approval

Using Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "TurboAiLabs/turbo-ai-7b"

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto"
)

messages = [
    {
        "role": "system",
        "content": "You are Turbo AI, a helpful local email assistant."
    },
    {
        "role": "user",
        "content": "Summarize this email: Please review the attached contract and send your comments by Friday."
    }
]

inputs = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    inputs,
    max_new_tokens=256
)

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

Recommended System Prompt

You are Turbo AI, an advanced local-first email assistant.

Help users summarize emails, draft professional replies, classify intent, extract action items, detect deadlines, identify follow-ups, and understand email conversations.

Be concise, professional, privacy-aware, and never invent information that does not appear in the email.

Example Output

Input

Hi Sam,

Please submit the revised proposal before Friday, confirm whether you're available for Monday's client meeting, and upload the presentation to the shared drive.

Output

Action Items

1. Submit the revised proposal before Friday.
2. Confirm availability for Monday's client meeting.
3. Upload the presentation to the shared drive.

About TurboMail

TurboMail is a local-first desktop email client focused on privacy, speed, and AI-powered productivity.

Rather than sending sensitive email conversations to cloud AI providers, TurboMail is designed to perform as much AI processing locally as possible.

Turbo AI models make this possible by providing fast, practical language models optimized for email workflows.

About TurboAI Labs

TurboAI Labs develops practical AI models optimized for privacy-first productivity software.

Our focus is building efficient language models that balance performance, speed, and local deployment across personal devices and enterprise environments.

Turbo AI 7B represents our larger productivity model for users who need stronger reasoning and higher-quality writing while maintaining control over their data.

Limitations

Turbo AI 7B is optimized for productivity and email-related workflows.

Although it delivers stronger reasoning and writing than smaller edge models, it may still generate inaccurate or incomplete information.

Users should always review generated summaries, replies, extracted tasks, and classifications before relying on them for important decisions.

Disclaimer

Turbo AI 7B is intended to assist users with productivity and private email workflows.

Generated content may contain mistakes or omissions and should be reviewed before being used in business communication or decision-making.

Citation

If you use Turbo AI 7B in your research or application, please cite:

https://huggingface.co/TurboAiLabs/turbo-ai-7b

Built by TurboAI Labs for TurboMail ⚡️

Downloads last month: 878

Safetensors

Model size

8B params

Tensor type

F16

Model tree for TurboAiLabs/turbo-ai-7b

Quantizations

2 models

TurboAiLabs
/

turbo-ai-7b

Turbo AI 7B — Advanced Local Email Intelligence ⚡️

Why Turbo AI?

Key Benefits

Advanced Email Understanding

Privacy First

Long Context Understanding

Professional Writing

Flexible Deployment

Built for Productivity

Model Details

Intended Use Cases

Example Prompts

Email Summarization

Draft Reply

Task Extraction

Intent Classification

Using Transformers

Recommended System Prompt

Example Output

About TurboMail

About TurboAI Labs

Links

Limitations

Disclaimer

Citation

Model tree for TurboAiLabs/turbo-ai-7b