Instructions to use nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx with Transformers:

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

pipe = pipeline("image-text-to-text", model="nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx")
model = AutoModelForMultimodalLM.from_pretrained("nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx

SGLang

How to use nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx 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 "nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx" \
    --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": "nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx" \
        --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": "nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio

How to use nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx 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 nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx 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 nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx",
    max_seq_length=2048,
)

Docker Model Runner
How to use nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx with Docker Model Runner:
```
docker model run hf.co/nightmedia/unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx
```

unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx

This is the Deckard(qx) formula that uses data stores and most attention paths in low precision(6 bit), enhancing vital attention paths, head, context, and embeddings to 8 bit.

I am still evaluating this quant, here is a LinkedIn review of one of my pictures with the unsloth-Qwen3-VL-8B-Instruct-qx86x-hi-mlx

This model unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx was converted to MLX format from unsloth/Qwen3-VL-2B-Instruct using mlx-lm version 0.28.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("unsloth-Qwen3-VL-2B-Instruct-qx86x-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)