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
```

dbaek111 commited on 10 days ago

Commit

babd32c

verified ·

1 Parent(s): 0f9b52d

Update benchmark tables with 512px and 1024px comparison

Browse files

Files changed (1) hide show

README.md +34 -15

README.md CHANGED Viewed

@@ -63,25 +63,44 @@ python -m mlx_vlm.generate \
 ## 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

 ## 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