Instructions to use dbaek111/fastvlm-7b-mlx-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbaek111/fastvlm-7b-mlx-q4 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-7b-mlx-q4")
config = load_config("dbaek111/fastvlm-7b-mlx-q4")

# 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-7b-mlx-q4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="dbaek111/fastvlm-7b-mlx-q4", 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-7b-mlx-q4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use dbaek111/fastvlm-7b-mlx-q4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbaek111/fastvlm-7b-mlx-q4"
# 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-7b-mlx-q4",
		"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-7b-mlx-q4

SGLang

How to use dbaek111/fastvlm-7b-mlx-q4 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-7b-mlx-q4" \
    --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-7b-mlx-q4",
		"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-7b-mlx-q4" \
        --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-7b-mlx-q4",
		"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"
						}
					}
				]
			}
		]
	}'

How to use dbaek111/fastvlm-7b-mlx-q4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dbaek111/fastvlm-7b-mlx-q4"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "dbaek111/fastvlm-7b-mlx-q4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dbaek111/fastvlm-7b-mlx-q4 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dbaek111/fastvlm-7b-mlx-q4"

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 dbaek111/fastvlm-7b-mlx-q4

Run Hermes

hermes

OpenClaw new

How to use dbaek111/fastvlm-7b-mlx-q4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dbaek111/fastvlm-7b-mlx-q4"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "dbaek111/fastvlm-7b-mlx-q4" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use dbaek111/fastvlm-7b-mlx-q4 with Docker Model Runner:
```
docker model run hf.co/dbaek111/fastvlm-7b-mlx-q4
```

fastvlm-7b-mlx-q4 / README.md

dbaek111

Update benchmark tables with 512px and 1024px comparison

babd32c verified 11 days ago

preview code

Raw

History Blame

3.99 kB

	---
	license: apple-amlr
	library_name: mlx
	pipeline_tag: image-text-to-text
	base_model: apple/FastVLM-7B
	base_model_relation: quantized
	tags:
	- fastvlm
	- mlx
	- mlx-vlm
	- safetensors
	- transformers
	- llava_qwen2
	- image-text-to-text
	- text-generation
	- conversational
	- custom_code
	- vision-language
	- multimodal
	- apple-silicon
	- quantized
	- 7B
	- q4 / 4-bit quantized
	- 4-bit
	- 4-bit precision
	- q4
	---

	# fastvlm-7b-mlx-q4

	This repository contains an MLX-converted FastVLM checkpoint.

	## Model

	- Base model: `apple/FastVLM-7B`
	- Parameters: `7B`
	- Precision: `q4 / 4-bit quantized`
	- Approx. folder size: `4.9G`

	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

	```bash
	hf download dbaek111/fastvlm-7b-mlx-q4 --local-dir ./fastvlm-7b-mlx-q4

	python -m mlx_vlm.generate \
	--model ./fastvlm-7b-mlx-q4 \
	--image /path/to/your/image.jpg \
	--prompt "Explain the image." \
	--max-tokens 64 \
	--temp 0.0
	```

	## Benchmark

	Benchmarked on an Apple Silicon Mac with the patched FastVLM `mlx-vlm` workflow.

	- Task: pedestrian wayfinding captioning
	- Images: three local test images resized to 512px and 1024px long edge
	- 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`
	- Timing: model loaded once per image set, then three images processed sequentially

	### Model Selection

	\| Model \| Size \| Precision \| Avg 512px \| Avg 1024px \| Load \| Recommended use \|
	\|---\|---:\|---\|---:\|---:\|---:\|---\|
	\| fastvlm-0.5b-mlx-q4 \| 819M \| q4 \| 0.338s \| 0.370s \| 2.82s \| Smallest and fastest; rough real-time captions \|
	\| fastvlm-0.5b-mlx-q8 \| 1.1G \| q8 \| 0.419s \| 0.414s \| 2.57s \| Fast, with richer captions than 0.5B q4 \|
	\| fastvlm-0.5b-mlx-fp16 \| 1.6G \| fp16 \| 0.435s \| 0.421s \| 2.79s \| Small FP16 baseline \|
	\| fastvlm-1.5b-mlx-q4 \| 1.4G \| q4 \| 0.447s \| 0.464s \| 2.65s \| Best real-time balance for pedestrian wayfinding \|
	\| fastvlm-1.5b-mlx-q8 \| 2.2G \| q8 \| 0.552s \| 0.541s \| 2.68s \| More detail while staying sub-second \|
	\| fastvlm-1.5b-mlx-fp16 \| 3.8G \| fp16 \| 0.636s \| 0.557s \| 3.08s \| 1.5B FP16 reference variant \|
	\| fastvlm-7b-mlx-q4 \| 4.9G \| q4 \| 1.263s \| 1.241s \| 3.04s \| Best quality/latency tradeoff among 7B variants \|
	\| fastvlm-7b-mlx-q8 \| 8.0G \| q8 \| 1.497s \| 1.495s \| 3.85s \| Higher precision 7B, slower than q4 \|
	\| fastvlm-7b-mlx-fp16 \| 15G \| fp16 \| 1.834s \| 1.874s \| 45.48s \| Full precision reference; expensive to load \|

	### Per-Image Timing

	Each cell is `img1 / img2 / img3` inference time in seconds.

	\| Model \| 512px images \| 1024px images \|
	\|---\|---:\|---:\|
	\| fastvlm-0.5b-mlx-q4 \| 0.318 / 0.353 / 0.343 \| 0.374 / 0.370 / 0.366 \|
	\| fastvlm-0.5b-mlx-q8 \| 0.393 / 0.465 / 0.400 \| 0.424 / 0.387 / 0.431 \|
	\| fastvlm-0.5b-mlx-fp16 \| 0.394 / 0.490 / 0.421 \| 0.430 / 0.395 / 0.437 \|
	\| fastvlm-1.5b-mlx-q4 \| 0.454 / 0.458 / 0.430 \| 0.465 / 0.472 / 0.456 \|
	\| fastvlm-1.5b-mlx-q8 \| 0.591 / 0.611 / 0.453 \| 0.594 / 0.552 / 0.477 \|
	\| fastvlm-1.5b-mlx-fp16 \| 0.701 / 0.709 / 0.496 \| 0.520 / 0.635 / 0.516 \|
	\| fastvlm-7b-mlx-q4 \| 1.161 / 1.330 / 1.297 \| 1.081 / 1.343 / 1.298 \|
	\| fastvlm-7b-mlx-q8 \| 1.364 / 1.639 / 1.487 \| 1.341 / 1.712 / 1.432 \|
	\| fastvlm-7b-mlx-fp16 \| 1.561 / 2.041 / 1.902 \| 1.595 / 2.277 / 1.749 \|

	## 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.