Instructions to use EZCon/FastVLM-1.5B-8bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EZCon/FastVLM-1.5B-8bit-mlx with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("EZCon/FastVLM-1.5B-8bit-mlx")
config = load_config("EZCon/FastVLM-1.5B-8bit-mlx")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Transformers

How to use EZCon/FastVLM-1.5B-8bit-mlx with Transformers:

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

pipe = pipeline("image-text-to-text", model="EZCon/FastVLM-1.5B-8bit-mlx", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("EZCon/FastVLM-1.5B-8bit-mlx", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use EZCon/FastVLM-1.5B-8bit-mlx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EZCon/FastVLM-1.5B-8bit-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": "EZCon/FastVLM-1.5B-8bit-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/EZCon/FastVLM-1.5B-8bit-mlx

SGLang

How to use EZCon/FastVLM-1.5B-8bit-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 "EZCon/FastVLM-1.5B-8bit-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": "EZCon/FastVLM-1.5B-8bit-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 "EZCon/FastVLM-1.5B-8bit-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": "EZCon/FastVLM-1.5B-8bit-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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use EZCon/FastVLM-1.5B-8bit-mlx with Docker Model Runner:
```
docker model run hf.co/EZCon/FastVLM-1.5B-8bit-mlx
```

May I know how to install mlx-vlm 0.3.10?

by neil0306 - opened Jan 26

Discussion

neil0306

Jan 26

Hi,
As stated in the title, the latest release version of the mlx-vlm repository as of January 26, 2026, is 0.3.9. How can I install the mlx-vlm 0.3.10 version?

Best,

hermeschen-ezcon

EZcon org Jan 27

•

edited Jan 27

You can easily install it from source (GitHub). However, even if you installed mlx_vlm from source to get the newest version, the model still isn’t working. It seems there’s a bug that needs fixing.
Oh, and there’s a little hiccup in the original model that I’m not sure Apple will sort out anytime soon. Perhaps it would be worth checking out some other models instead?

neil0306

Jan 27

Thanks for your reply!
I’ve now successfully installed 0.3.10 and can run inference.

I’d like to ask whether this model was exported from the official Apple FastVLM weights, and if so, is it the Stage 2 or Stage 3 version of the 1.5B model?

hermeschen-ezcon

EZcon org Jan 27

Yes, I converted from the official weight which is the 1.5B one. I'm not sure its stage, Apple doesn't mention it in the model card. If you want to get certain stage model, you need to go to the official GitHub Repo to download the convert it.

And actually you can check the model card, there's a link to original model.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment