Instructions to use teolm30/fox-1.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teolm30/fox-1.6 with Transformers:

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

pipe = pipeline("text-generation", model="teolm30/fox-1.6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teolm30/fox-1.6")
model = AutoModelForCausalLM.from_pretrained("teolm30/fox-1.6")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use teolm30/fox-1.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "teolm30/fox-1.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "teolm30/fox-1.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/teolm30/fox-1.6

SGLang

How to use teolm30/fox-1.6 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 "teolm30/fox-1.6" \
    --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": "teolm30/fox-1.6",
		"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 "teolm30/fox-1.6" \
        --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": "teolm30/fox-1.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use teolm30/fox-1.6 with Docker Model Runner:
```
docker model run hf.co/teolm30/fox-1.6
```

Fox 1.6

Fox 1.6 is a compact, device-friendly fork of Qwen/Qwen3-1.7B for general-purpose text generation.

What this repo is

A lightweight Hugging Face model repo with real weights and tokenizer files
Intended to be easier to deploy on consumer hardware than much larger LLMs
Branded and published under the Fox 1.6 name

What this repo is not

It is not trained from scratch here
It is not a claim that the model beats every large frontier model
It is a fork of the upstream Qwen 3 1.7B checkpoint

Intended use

On-device or low-footprint inference
Assistant-style chat and completion
Rapid experimentation with a compact base model

Notes

If you want Fox 1.6 to become a genuinely new model, the next step is to fine-tune this fork on a curated instruction dataset and evaluate it against your target benchmarks.

🤖 Run with Ollama

ollama run hf.co/teolm30/fox-1.6

Downloads last month: 160

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for teolm30/fox-1.6

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Finetuned

(789)

this model