Instructions to use NobodyWho/LFM2.5-VL-450M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NobodyWho/LFM2.5-VL-450M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NobodyWho/LFM2.5-VL-450M-GGUF",
	filename="LFM2.5-VL-450M-F16-vendor-sampling.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NobodyWho/LFM2.5-VL-450M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16

Use Docker

docker model run hf.co/NobodyWho/LFM2.5-VL-450M-GGUF:F16

LM Studio
Jan

vLLM

How to use NobodyWho/LFM2.5-VL-450M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NobodyWho/LFM2.5-VL-450M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NobodyWho/LFM2.5-VL-450M-GGUF",
		"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/NobodyWho/LFM2.5-VL-450M-GGUF:F16

Ollama
How to use NobodyWho/LFM2.5-VL-450M-GGUF with Ollama:
```
ollama run hf.co/NobodyWho/LFM2.5-VL-450M-GGUF:F16
```

Unsloth Studio

How to use NobodyWho/LFM2.5-VL-450M-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for NobodyWho/LFM2.5-VL-450M-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for NobodyWho/LFM2.5-VL-450M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NobodyWho/LFM2.5-VL-450M-GGUF to start chatting

How to use NobodyWho/LFM2.5-VL-450M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "NobodyWho/LFM2.5-VL-450M-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NobodyWho/LFM2.5-VL-450M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf NobodyWho/LFM2.5-VL-450M-GGUF:F16

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 NobodyWho/LFM2.5-VL-450M-GGUF:F16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use NobodyWho/LFM2.5-VL-450M-GGUF with Docker Model Runner:
```
docker model run hf.co/NobodyWho/LFM2.5-VL-450M-GGUF:F16
```

Lemonade

How to use NobodyWho/LFM2.5-VL-450M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NobodyWho/LFM2.5-VL-450M-GGUF:F16

Run and chat with the model

lemonade run user.LFM2.5-VL-450M-GGUF-F16

List all available models

lemonade list

LFM2.5-VL-450M GGUF — with vendor sampling metadata

GGUF builds of LiquidAI/LFM2.5-VL-450M prepared for tool calling. Unlike most LFM GGUFs, this model ships a complete native chat template (it already renders the tool_calls field), so no template change was needed. Every file is the corresponding upstream quant with bit-identical weight tensors and one metadata addition: LiquidAI's recommended sampling settings embedded as general.sampling.* (temp=0.1, min_p=0.15, penalty_repeat=1.05).

This is the smallest tool-capable LFM — a practical edge-device tool-caller at 219-711 MB.

Model Capabilities

Text generation — instruction-following chat model
Tool calling — native LFM2 function-calling format, including multi-turn tool use
Vision — understands and reasons about images (pair with the upstream mmproj file, see Getting Started)
Long context — 128k tokens

Getting Started

Running this model with nobodywho requires the upcoming release (PR #564): its native chat template uses HuggingFace {% generation %} tags that nobodywho ≤ 1.4.0 cannot parse, and LFM tool calling ships in the same release. The files work in any other llama.cpp-based runtime; the original unmodified GGUFs live in the upstream LiquidAI/LFM2.5-VL-450M-GGUF repo.

Install NobodyWho:

pip install nobodywho

Run — the model is downloaded and cached automatically on first use:

from nobodywho import Chat

chat = Chat("huggingface:NobodyWho/LFM2.5-VL-450M-GGUF/LFM2.5-VL-450M-Q8_0-vendor-sampling.gguf")
response = chat.ask("What is the capital of Denmark?").completed()
print(response) # Copenhagen!

Tool calling

from nobodywho import Chat, tool

@tool(description="Gets the current weather for a city")
def get_weather(city: str) -> str:
    return f"It is sunny and 22°C in {city}."

chat = Chat(
    "huggingface:NobodyWho/LFM2.5-VL-450M-GGUF/LFM2.5-VL-450M-Q8_0-vendor-sampling.gguf",
    tools=[get_weather],
)
print(chat.ask("What is the weather in Paris?").completed())

Vision

This repo now hosts the language model and the matching projection models (mmproj) — pass one as projection_model_path for image input. Two precisions are available: mmproj-LFM2.5-VL-450m-F16.gguf and a smaller mmproj-LFM2.5-VL-450m-Q8_0.gguf (either pairs with any model quant):

from nobodywho import Model, Chat, Prompt, Image, Text

model = Model(
    "huggingface:NobodyWho/LFM2.5-VL-450M-GGUF/LFM2.5-VL-450M-Q8_0-vendor-sampling.gguf",
    projection_model_path="huggingface:NobodyWho/LFM2.5-VL-450M-GGUF/mmproj-LFM2.5-VL-450m-F16.gguf",
)
chat = Chat(model, system_prompt="You are a helpful assistant.")

prompt = Prompt([
    Text("What do you see in this image?"),
    Image("./photo.png"),
])
response = chat.ask(prompt).completed()
print(response)

Files

Scores on NobodyWho's 14-test tool-calling suite. "metadata active" = runtimes that read sampler defaults from the model file; "ignored" = runtimes that don't (the embedded sampling consistently gains one test on this model).

File	metadata active	metadata ignored
`LFM2.5-VL-450M-Q8_0-vendor-sampling.gguf` (379 MB)	13/14	12/14
`LFM2.5-VL-450M-F16-vendor-sampling.gguf` (711 MB)	13/14	12/14
`LFM2.5-VL-450M-Q4_0-vendor-sampling.gguf` (219 MB)	12/14	11/14

The one consistent failure at the top configurations is a single test where the model calls the right tool but garbles a string inside a tuple-typed argument — verified stable across quants up to F16. No refusals, no crashes.

Use

Verified with NobodyWho (see PR #564); works in any llama.cpp-based runtime. Text-only use needs no mmproj; for vision, pair with the mmproj-LFM2.5-VL-450m-* files hosted in this repo.

Model Details

Property	Value
Parameters	450M (354M language model + vision tower in the `mmproj`)
Context length	128,000 tokens
License	LFM Open License v1.0
Base model	LiquidAI/LFM2.5-VL-450M