Instructions to use mlx-community/LFM2-VL-3B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/LFM2-VL-3B-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="mlx-community/LFM2-VL-3B-4bit")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("mlx-community/LFM2-VL-3B-4bit")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/LFM2-VL-3B-4bit")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use mlx-community/LFM2-VL-3B-4bit 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("mlx-community/LFM2-VL-3B-4bit")
config = load_config("mlx-community/LFM2-VL-3B-4bit")

# 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)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use mlx-community/LFM2-VL-3B-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/LFM2-VL-3B-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/LFM2-VL-3B-4bit",
		"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/mlx-community/LFM2-VL-3B-4bit

SGLang

How to use mlx-community/LFM2-VL-3B-4bit 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 "mlx-community/LFM2-VL-3B-4bit" \
    --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": "mlx-community/LFM2-VL-3B-4bit",
		"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 "mlx-community/LFM2-VL-3B-4bit" \
        --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": "mlx-community/LFM2-VL-3B-4bit",
		"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 mlx-community/LFM2-VL-3B-4bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/LFM2-VL-3B-4bit
```

LFM2-VL-3B-4bit / config.json

prince-canuma

Upload folder using huggingface_hub

1e3ae77 verified 7 months ago

raw

history blame

3.3 kB

	{
	"architectures": [
	"Lfm2VlForConditionalGeneration"
	],
	"do_image_splitting": true,
	"downsample_factor": 2,
	"dtype": "bfloat16",
	"encoder_patch_size": 16,
	"image_token_id": 396,
	"max_image_tokens": 256,
	"max_pixels_tolerance": 2.0,
	"max_tiles": 10,
	"min_image_tokens": 64,
	"min_tiles": 2,
	"model_type": "lfm2_vl",
	"projector_bias": true,
	"projector_hidden_act": "gelu",
	"projector_hidden_size": 2560,
	"quantization": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 4,
	"mode": "affine"
	},
	"text_config": {
	"_name_or_path": "LiquidAI/LFM2-2.6B",
	"architectures": [
	"Lfm2ForCausalLM"
	],
	"block_auto_adjust_ff_dim": false,
	"block_dim": 2048,
	"block_ff_dim": 10752,
	"block_ffn_dim_multiplier": 1.0,
	"block_mlp_init_scale": 1.0,
	"block_multiple_of": 256,
	"block_norm_eps": 1e-05,
	"block_out_init_scale": 1.0,
	"block_use_swiglu": true,
	"block_use_xavier_init": true,
	"conv_L_cache": 3,
	"conv_bias": false,
	"conv_dim": 2048,
	"conv_dim_out": 2048,
	"conv_use_xavier_init": true,
	"dtype": "bfloat16",
	"eos_token_id": 7,
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 10752,
	"layer_types": [
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv"
	],
	"max_position_embeddings": 128000,
	"model_type": "lfm2",
	"norm_eps": 1e-05,
	"num_attention_heads": 32,
	"num_heads": 32,
	"num_hidden_layers": 30,
	"num_key_value_heads": 8,
	"rope_parameters": {
	"rope_theta": 1000000.0,
	"rope_type": "default"
	},
	"rope_theta": 1000000.0,
	"theta": 1000000.0,
	"tie_embedding": true,
	"use_cache": true,
	"use_pos_enc": true,
	"vocab_size": 65536
	},
	"tile_size": 512,
	"transformers_version": "4.57.1",
	"use_image_special_tokens": true,
	"use_thumbnail": true,
	"vision_config": {
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"intermediate_size": 4304,
	"layer_norm_eps": 1e-06,
	"model_type": "siglip2_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"num_patches": 256,
	"patch_size": 16,
	"vision_use_head": false
	}
	}