Instructions to use lazos/lfm2.5-350m-frontend-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lazos/lfm2.5-350m-frontend-agent with Transformers:

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

pipe = pipeline("text-generation", model="lazos/lfm2.5-350m-frontend-agent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lazos/lfm2.5-350m-frontend-agent")
model = AutoModelForCausalLM.from_pretrained("lazos/lfm2.5-350m-frontend-agent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use lazos/lfm2.5-350m-frontend-agent with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lazos/lfm2.5-350m-frontend-agent",
	filename="lfm2.5-350m-frontend-agent-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lazos/lfm2.5-350m-frontend-agent with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M

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 lazos/lfm2.5-350m-frontend-agent:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M

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 lazos/lfm2.5-350m-frontend-agent:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M

Use Docker

docker model run hf.co/lazos/lfm2.5-350m-frontend-agent:Q4_K_M

LM Studio
Jan

vLLM

How to use lazos/lfm2.5-350m-frontend-agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lazos/lfm2.5-350m-frontend-agent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lazos/lfm2.5-350m-frontend-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lazos/lfm2.5-350m-frontend-agent:Q4_K_M

SGLang

How to use lazos/lfm2.5-350m-frontend-agent 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 "lazos/lfm2.5-350m-frontend-agent" \
    --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": "lazos/lfm2.5-350m-frontend-agent",
		"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 "lazos/lfm2.5-350m-frontend-agent" \
        --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": "lazos/lfm2.5-350m-frontend-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use lazos/lfm2.5-350m-frontend-agent with Ollama:
```
ollama run hf.co/lazos/lfm2.5-350m-frontend-agent:Q4_K_M
```

Unsloth Studio

How to use lazos/lfm2.5-350m-frontend-agent 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 lazos/lfm2.5-350m-frontend-agent 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 lazos/lfm2.5-350m-frontend-agent to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lazos/lfm2.5-350m-frontend-agent to start chatting

How to use lazos/lfm2.5-350m-frontend-agent with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M

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": "lazos/lfm2.5-350m-frontend-agent:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lazos/lfm2.5-350m-frontend-agent with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M

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 lazos/lfm2.5-350m-frontend-agent:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use lazos/lfm2.5-350m-frontend-agent with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lazos/lfm2.5-350m-frontend-agent:Q4_K_M

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 "lazos/lfm2.5-350m-frontend-agent:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --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 lazos/lfm2.5-350m-frontend-agent with Docker Model Runner:
```
docker model run hf.co/lazos/lfm2.5-350m-frontend-agent:Q4_K_M
```

Lemonade

How to use lazos/lfm2.5-350m-frontend-agent with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lazos/lfm2.5-350m-frontend-agent:Q4_K_M

Run and chat with the model

lemonade run user.lfm2.5-350m-frontend-agent-Q4_K_M

List all available models

lemonade list

frontend-agent - LFM2.5-350M (v1.3.0, bounded)

A generic English web/front-end agent fine-tuned from LiquidAI/LFM2.5-350M, small enough to run entirely in the browser (edge / wllama, no server-side model).

Sibling model: for the smallest / fastest build, see the 230M variant - lazos/lfm2.5-230m-frontend-agent. The 350M offers more headroom at ~1.5x the footprint; pick per device budget.

Bounded context

A stateless, context-bounded agent. It grounds every turn in a compact context block C the host app injects: the current VIEW (items on screen, with ids + prices), the CART, and any relevant KNOWLEDGE. The model reads and acts on exactly what it is given - add/remove by the shown id, answer prices from the view, resolve references like "the second one", list what's actually there - and does not invent items. The app re-injects C each turn (the model holds no state).

Pair it with the npm library frontend-agent, whose ContextManager renders C in the exact format the model was trained on (a shared, versioned contract).

What's new in v1.3.0

Beyond-view resolution. For an item not on screen, the model now searches by name first (list_items / get_item) before acting, instead of grabbing a look-alike id already in view - fixes both beyond-view add and beyond-view price lookups.
Filtering with a view present. "under $30" / category constraints populate the advertised list_items filters even when items are already on screen.
Off-scope steering + small talk. Genuinely off-topic asks get a brief decline plus a nudge to what the agent can do; social small talk gets a short in-character reply - both learned as a pattern (never a fixed anti-topic list), so they generalize to unseen inputs.
Quantity / unit disambiguation. A number embedded in a title ("18g Basket") is no longer misread as a quantity.
Open-license training data. Synthetic data distilled from Apache-2.0 / MIT teachers (Qwen2.5-7B + Qwen3-30B-A3B, via OpenRouter) - no proprietary-model output in the dataset.

Usage

Serve a GGUF in-browser via wllama; each turn, build the system prompt from the library's ContextManager (persona + VIEW/CART/KNOWLEDGE) and advertise your tool schemas. See the project repo for the runtime wiring. Or fine-tune further from the transformers checkpoint (model.safetensors).

Files

File	Format	Size
`model.safetensors`	bf16 (transformers, resumable)	~676 MB
`*-Q8_0.gguf`	GGUF (near-lossless)	~362 MB
`*-Q6_K.gguf`	GGUF	~280 MB
`*-Q4_K_M.gguf`	GGUF (smallest, browser default)	~219 MB

Trained on the lazos/frontend-agent-sft dataset (v1.3.0).

License

Fine-tune of LFM2.5-350M; inherits the LFM Open License 1.0 (see LICENSE/NOTICE). Training data is fully synthetic (open-license teachers).

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for lazos/lfm2.5-350m-frontend-agent

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

LiquidAI/LFM2.5-350M

Finetuned

(52)

this model