Instructions to use apple/FastVLM-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apple/FastVLM-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="apple/FastVLM-0.5B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("apple/FastVLM-0.5B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use apple/FastVLM-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "apple/FastVLM-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "apple/FastVLM-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/apple/FastVLM-0.5B

SGLang

How to use apple/FastVLM-0.5B 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 "apple/FastVLM-0.5B" \
    --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": "apple/FastVLM-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "apple/FastVLM-0.5B" \
        --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": "apple/FastVLM-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use apple/FastVLM-0.5B with Docker Model Runner:
```
docker model run hf.co/apple/FastVLM-0.5B
```

pcuenq HF Staff commited on Oct 18, 2025

Commit

3bdf25c

1 Parent(s): e61e70b

Explicit vision_config

Browse files

Files changed (1) hide show

config.json +20 -1

config.json CHANGED Viewed

@@ -45,5 +45,24 @@
   "use_cache": true,
   "use_mm_proj": true,
   "use_sliding_window": false,
   "vocab_size": 151936
-}

   "use_cache": true,
   "use_mm_proj": true,
   "use_sliding_window": false,
+  "vision_config": {
+    "cls_ratio": 2.0,
+    "down_patch_size": 7,
+    "down_stride": 2,
+    "downsamples": [true, true, true, true, true],
+    "embed_dims": [96, 192, 384, 768, 1536],
+    "hidden_size": 1024,
+    "image_size": 1024,
+    "intermediate_size": 3072,
+    "layer_scale_init_value": 1e-5,
+    "layers": [2, 12, 24, 4, 2],
+    "mlp_ratios": [4, 4, 4, 4, 4],
+    "num_classes": 1000,
+    "patch_size": 64,
+    "pos_embs_shapes": [null, null, null, [7, 7], [7, 7]],
+    "projection_dim": 768,
+    "repmixer_kernel_size": 3,
+    "token_mixers": ["repmixer", "repmixer", "repmixer", "attention", "attention"]
+  },
   "vocab_size": 151936
+}