Instructions to use lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit")
model = AutoModelForMultimodalLM.from_pretrained("lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit", device_map="auto")
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 lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit 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("lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit")
config = load_config("lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit")

# 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 Settings
LM Studio

vLLM

How to use lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit",
		"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/lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit

SGLang

How to use lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit 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 "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit" \
    --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": "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit",
		"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 "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit" \
        --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": "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit",
		"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 lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit"

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": "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit 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 "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit"

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 lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit

Run Hermes

hermes

OpenClaw new

How to use lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit"

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 "lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit" \
  --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 lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit with Docker Model Runner:
```
docker model run hf.co/lmstudio-community/LFM2.5-VL-1.6B-MLX-8bit
```

LFM2.5-VL-1.6B-MLX-8bit / tokenizer_config.json

lmmy

Add files using upload-large-folder tool

b3d71f9 verified 7 months ago

Raw

History Blame Contribute Delete

5.37 kB

	{
	"additional_special_tokens": null,
	"backend": "tokenizers",
	"bos_token": "<\|startoftext\|>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|im_end\|>",
	"extra_special_tokens": [],
	"image_end_token": "<\|image_end\|>",
	"image_start_token": "<\|image_start\|>",
	"image_thumbnail": "<\|img_thumbnail\|>",
	"image_token": "<image>",
	"is_local": true,
	"legacy": false,
	"model_max_length": 1000000000000000019884624838656,
	"model_specific_special_tokens": {
	"image_end_token": "<\|image_end\|>",
	"image_start_token": "<\|image_start\|>",
	"image_thumbnail": "<\|img_thumbnail\|>",
	"image_token": "<image>"
	},
	"pad_token": "<\|pad\|>",
	"processor_class": "Lfm2VlProcessor",
	"return_token_type_ids": false,
	"sp_model_kwargs": {},
	"spaces_between_special_tokens": false,
	"tokenizer_class": "TokenizersBackend",
	"use_default_system_prompt": false,
	"use_fast": true,
	"chat_template": "{{- bos_token -}}\n{%- set keep_past_thinking = keep_past_thinking \| default(false) -%}\n{%- set ns = namespace(system_prompt=\"\") -%}\n{%- if messages[0][\"role\"] == \"system\" -%}\n {%- set ns.system_prompt = messages[0][\"content\"] -%}\n {%- set messages = messages[1:] -%}\n{%- endif -%}\n{%- if tools -%}\n {%- set ns.system_prompt = ns.system_prompt + (\"\\n\" if ns.system_prompt else \"\") + \"List of tools: [\" -%}\n {%- for tool in tools -%}\n {%- if tool is not string -%}\n {%- set tool = tool \| tojson -%}\n {%- endif -%}\n {%- set ns.system_prompt = ns.system_prompt + tool -%}\n {%- if not loop.last -%}\n {%- set ns.system_prompt = ns.system_prompt + \", \" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- set ns.system_prompt = ns.system_prompt + \"]\" -%}\n{%- endif -%}\n{%- if ns.system_prompt -%}\n {{- \"<\|im_start\|>system\\n\" + ns.system_prompt + \"<\|im_end\|>\\n\" -}}\n{%- endif -%}\n{%- set ns.last_assistant_index = -1 -%}\n{%- for message in messages -%}\n {%- if message[\"role\"] == \"assistant\" -%}\n {%- set ns.last_assistant_index = loop.index0 -%}\n {%- endif -%}\n{%- endfor -%}\n{%- for message in messages -%}\n {{- \"<\|im_start\|>\" + message[\"role\"] + \"\\n\" -}}\n {%- if message.get('tool_calls') %}\n {# \u2500\u2500\u2500\u2500\u2500 create a list to append tool calls to \u2500\u2500\u2500\u2500\u2500 #}\n {%- set tool_calls_ns = namespace(tool_calls=[])%}\n {%- for tool_call in message['tool_calls'] %}\n {%- set func_name = tool_call['function']['name'] %}\n {%- set func_args = tool_call['function']['arguments'] %}\n {# \u2500\u2500\u2500\u2500\u2500 create a list of func_arg strings to accumulate for each tool call \u2500\u2500\u2500\u2500\u2500 #}\n {%- set args_ns = namespace(arg_strings=[])%}\n {%- for arg_name, arg_value in func_args.items() %}\n {%- if arg_value is none %}\n {%- set formatted_arg_value = 'null' %}\n {%- elif arg_value is boolean %}\n {%- set formatted_arg_value = 'True' if arg_value else 'False' %}\n {%- elif arg_value is string %}\n {%- set formatted_arg_value = '\"' ~ arg_value ~ '\"' %}\n {%- elif arg_value is mapping or arg_value is iterable %}\n {%- set formatted_arg_value = arg_value \| tojson %}\n {%- else %}\n {%- set formatted_arg_value = arg_value \| string %}\n {%- endif %}\n {# \u2500\u2500\u2500\u2500\u2500 format each argument key,value pair \u2500\u2500\u2500\u2500\u2500 #}\n {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name ~ '=' ~ formatted_arg_value] %}\n {%- endfor %}\n {# \u2500\u2500\u2500\u2500\u2500 append each formatted tool call \u2500\u2500\u2500\u2500\u2500 #}\n {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [(func_name + '(' + (args_ns.arg_strings \| join(\", \")) + ')' )]%}\n {%- endfor %}\n {# \u2500\u2500\u2500\u2500\u2500 format the final tool calls \u2500\u2500\u2500\u2500\u2500 #}\n {{-'<\|tool_call_start\|>[' + (tool_calls_ns.tool_calls \| join(\", \")) + ']<\|tool_call_end\|>'}}\n {%- endif %}\n {%- set content = message[\"content\"] -%}\n {%- if content is not string -%}\n {%- set ns.content = \"\" -%}\n {%- for item in content -%}\n {%- if item[\"type\"] == \"image\" -%}\n {%- set ns.content = ns.content + \"<image>\" -%}\n {%- elif item[\"type\"] == \"text\" -%}\n {%- set ns.content = ns.content + item[\"text\"] -%}\n {%- else -%}\n {%- set ns.content = ns.content + item \| tojson -%}\n {%- endif -%}\n {%- endfor -%}\n {%- set content = ns.content -%}\n {%- endif -%}\n {%- if message[\"role\"] == \"assistant\" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}\n {%- if \"</think>\" in content -%}\n {%- set content = content.split(\"</think>\")[-1] \| trim -%}\n {%- endif -%}\n {%- endif -%}\n {{- content + \"<\|im_end\|>\\n\" -}}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{- \"<\|im_start\|>assistant\\n\" -}}\n{%- endif -%}\n"
	}