Instructions to use dbaek111/fastvlm-1.5b-mlx-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbaek111/fastvlm-1.5b-mlx-q8 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("dbaek111/fastvlm-1.5b-mlx-q8")
config = load_config("dbaek111/fastvlm-1.5b-mlx-q8")

# 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 dbaek111/fastvlm-1.5b-mlx-q8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="dbaek111/fastvlm-1.5b-mlx-q8", 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("dbaek111/fastvlm-1.5b-mlx-q8", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use dbaek111/fastvlm-1.5b-mlx-q8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbaek111/fastvlm-1.5b-mlx-q8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbaek111/fastvlm-1.5b-mlx-q8",
		"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/dbaek111/fastvlm-1.5b-mlx-q8

SGLang

How to use dbaek111/fastvlm-1.5b-mlx-q8 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 "dbaek111/fastvlm-1.5b-mlx-q8" \
    --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": "dbaek111/fastvlm-1.5b-mlx-q8",
		"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 "dbaek111/fastvlm-1.5b-mlx-q8" \
        --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": "dbaek111/fastvlm-1.5b-mlx-q8",
		"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 dbaek111/fastvlm-1.5b-mlx-q8 with Docker Model Runner:
```
docker model run hf.co/dbaek111/fastvlm-1.5b-mlx-q8
```

fastvlm-1.5b-mlx-q8

This repository contains an MLX-converted FastVLM checkpoint.

Model

Base model: apple/FastVLM-1.5B
Parameters: 1.5B
Precision: q8 / 8-bit quantized
Approx. folder size: 2.2G

The checkpoint was converted from Apple FastVLM using the official FastVLM model export workflow and patched mlx-vlm.

Files

This repository should include:

config.json
MLX model weights
tokenizer files
fastvithd.mlpackage vision tower

Example Usage

hf download dbaek111/fastvlm-1.5b-mlx-q8 --local-dir ./fastvlm-1.5b-mlx-q8

python -m mlx_vlm.generate \
  --model ./fastvlm-1.5b-mlx-q8 \
  --image /path/to/your/image.jpg \
  --prompt "Explain the image." \
  --max-tokens 64 \
  --temp 0.0

Benchmark

Benchmark condition:

Images: three 512px pedestrian wayfinding test images
Prompt: Describe what is visible for pedestrian wayfinding in one short sentence. Do not list categories. Do not mention anything you cannot see. Keep under 30 words.
Max tokens: 64
Temperature: 0.0
Model loaded once, then images processed sequentially

Model	Size	Load	Img1	Img2	Img3	Avg
fastvlm-0.5b-mlx-q4	819M	2.85s	0.299s	0.351s	0.338s	0.330s
fastvlm-0.5b-mlx-q8	1.1G	2.78s	0.382s	0.459s	0.396s	0.412s
fastvlm-0.5b-mlx-fp16	1.6G	2.93s	0.529s	0.478s	0.407s	0.471s
fastvlm-1.5b-mlx-q4	1.4G	2.46s	0.454s	0.462s	0.443s	0.453s
fastvlm-1.5b-mlx-q8	2.2G	2.49s	0.607s	0.592s	0.477s	0.559s
fastvlm-1.5b-mlx-fp16	3.8G	2.83s	0.702s	0.706s	0.567s	0.658s
fastvlm-7b-mlx-q4	4.9G	3.00s	1.139s	1.303s	1.277s	1.239s
fastvlm-7b-mlx-q8	8.0G	3.67s	1.324s	1.583s	1.438s	1.448s
fastvlm-7b-mlx-fp16	15G	46.07s	1.536s	2.004s	1.885s	1.808s

Compatibility

This is an MLX export of FastVLM for Apple Silicon Macs. It includes the CoreML FastViTHD vision tower as fastvithd.mlpackage.

This repository is not a standard PyTorch Transformers checkpoint and is not intended for vLLM, SGLang, or Linux GPU inference.

Notes

This is a converted and quantized derivative of Apple FastVLM.

Please refer to the original Apple FastVLM repository and model card for license and usage conditions.

Downloads last month: 72

Safetensors

Model size

0.5B params

Tensor type

F16

U32

MLX

Hardware compatibility

8-bit

Model tree for dbaek111/fastvlm-1.5b-mlx-q8

Base model

apple/FastVLM-1.5B

Quantized

(5)

this model

Collection including dbaek111/fastvlm-1.5b-mlx-q8

FastVLM MLX Exports

Collection

MLX-converted FastVLM checkpoints for Apple Silicon Macs, including 0.5B, 1.5B, and 7B variants in q4, q8, and fp16. • 9 items • Updated about 11 hours ago