Instructions to use qforge/Qwen3-14B-AT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qforge/Qwen3-14B-AT with Transformers:

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

pipe = pipeline("text-generation", model="qforge/Qwen3-14B-AT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qforge/Qwen3-14B-AT")
model = AutoModelForCausalLM.from_pretrained("qforge/Qwen3-14B-AT")
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 qforge/Qwen3-14B-AT with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="qforge/Qwen3-14B-AT",
	filename="unsloth.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 qforge/Qwen3-14B-AT with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf qforge/Qwen3-14B-AT:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf qforge/Qwen3-14B-AT:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf qforge/Qwen3-14B-AT:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf qforge/Qwen3-14B-AT: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 qforge/Qwen3-14B-AT:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf qforge/Qwen3-14B-AT: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 qforge/Qwen3-14B-AT:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf qforge/Qwen3-14B-AT:Q4_K_M

Use Docker

docker model run hf.co/qforge/Qwen3-14B-AT:Q4_K_M

LM Studio
Jan

vLLM

How to use qforge/Qwen3-14B-AT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qforge/Qwen3-14B-AT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qforge/Qwen3-14B-AT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qforge/Qwen3-14B-AT:Q4_K_M

SGLang

How to use qforge/Qwen3-14B-AT 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 "qforge/Qwen3-14B-AT" \
    --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": "qforge/Qwen3-14B-AT",
		"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 "qforge/Qwen3-14B-AT" \
        --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": "qforge/Qwen3-14B-AT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use qforge/Qwen3-14B-AT with Ollama:
```
ollama run hf.co/qforge/Qwen3-14B-AT:Q4_K_M
```

Unsloth Studio

How to use qforge/Qwen3-14B-AT 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 qforge/Qwen3-14B-AT 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 qforge/Qwen3-14B-AT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for qforge/Qwen3-14B-AT to start chatting

How to use qforge/Qwen3-14B-AT with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf qforge/Qwen3-14B-AT: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": "qforge/Qwen3-14B-AT:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use qforge/Qwen3-14B-AT with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf qforge/Qwen3-14B-AT: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 qforge/Qwen3-14B-AT:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use qforge/Qwen3-14B-AT with Docker Model Runner:
```
docker model run hf.co/qforge/Qwen3-14B-AT:Q4_K_M
```

Lemonade

How to use qforge/Qwen3-14B-AT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull qforge/Qwen3-14B-AT:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-14B-AT-Q4_K_M

List all available models

lemonade list

1. Qwen3-14B Async Tools Model

DEMO https://youtu.be/CyHbX13AuK0

Finetuned from model: unsloth/Qwen3-14B-unsloth-bnb-4bit using AsyncTool dataset

💡 Why Async Tools?

Real-world AI agents often need to:

Call external APIs with variable latency
Query databases that take time to respond
Execute long-running computations
Handle multiple tool calls in parallel
Provide responsive user experiences without blocking

This model handles asynchronous tool execution — a critical capability for building responsive, real-world AI agents. Unlike traditional function-calling models that assume tools return results immediately, this model understands and properly handles tools that take time to execute and return results later during conversation.

🔄 Async Tool Call Protocol

The model implements a robust async protocol:

Tool Call: The model makes a function/tool call
ACK (Acknowledgment): The tool immediately returns <tool_ack id="tN"/> to confirm the request is received
Processing: The tool executes asynchronously (could be API calls, database queries, external services)
RESPONSE: The tool returns the actual result later

📋 Example Conversation Flow

User ask question

"Could you verify if Makani number 2871442438 is valid?"

Assistant makes tool call:

[
  {
    "id": "t1",
    "name": "IsValidMakani",
    "arguments": { "makaniNo": "2871442438" }
  }
]

Tool returns ACK:

<tool_ack id="t1"/>

Assistant provides interim response:

"Sure—checking that Makani number now. I'll get back to you as soon as I have the result."

User's message again

User: "Thanks"

Tool returns result:

{ "id": "t1", "ok": true, "data": { "isValid": true } }

Assistant provides final response:

"Great news! The Makani number 2871442438 is valid for the specified entrance in Dubai."

2. Video

https://youtu.be/CyHbX13AuK0

3. How we used Gemini and Pipecut?

Gemini

We used Gemini Speech to Text and are currently fine tuning Gemini 2.5 Flash Lite Model for the same task, improved latency and accuracy.

Pipecat

Link to implementation in Pipecat Pull Request.

5. Tell us what you did new during the hackathon

At the hackathon we've

improved AsyncTool dataset with more variety to improve quality of responses
fine tuned unsloth/Qwen3-14B-unsloth-bnb-4bit model using Google Colab (for handling Async Tools)
Prepared a draft (Pull Request) to Pipecat by adding support for our new model and native behaviour

🔧 Training Details

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

6. Feedback

At the beginning we had issues with running fine tuning on Google Vertex-ai (because of outdated documentation). Loved the test coverage and dev environment of pipecat.

Downloads last month: 43

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for qforge/Qwen3-14B-AT

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Quantized

unsloth/Qwen3-14B-unsloth-bnb-4bit

Quantized

(24)

this model