Instructions to use Duckets/LFM3-VL-2B-BrowserAgent-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Duckets/LFM3-VL-2B-BrowserAgent-GGUF 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 Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

Use Docker

docker model run hf.co/Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use Duckets/LFM3-VL-2B-BrowserAgent-GGUF with Ollama:
```
ollama run hf.co/Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0
```
Unsloth Desktop

How to use Duckets/LFM3-VL-2B-BrowserAgent-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Duckets/LFM3-VL-2B-BrowserAgent-GGUF with Docker Model Runner:
```
docker model run hf.co/Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0
```

Lemonade

How to use Duckets/LFM3-VL-2B-BrowserAgent-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

Run and chat with the model

lemonade run user.LFM3-VL-2B-BrowserAgent-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Duckets/LFM3-VL-2B-BrowserAgent-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

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 Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Duckets/LFM3-VL-2B-BrowserAgent-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0

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 "Duckets/LFM3-VL-2B-BrowserAgent-GGUF:Q8_0" \
  --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"

LFM3-VL-2B-BrowserAgent (GGUF Q8_0 + mmproj)

LiquidAI LFM3-VL-2B fine-tuned to operate BrowserOS and BrowserOS neo through their real MCP tool surfaces — snapshot → act → verify loops, batched form filling, tab/session management, error recovery, and the request_human_help discipline for logins, one-time codes, captchas, and money approvals. The vision tower is untouched by this text-only fine-tune and ships as the standard mmproj, so the model keeps its image understanding for screenshot-grounded browsing work.

Training data

1,553 training rows (+173 held-out eval), fully synthetic, built from the open-source browseros-ai/BrowserOS repo (tool definitions, the repo's own neo agent skill, and docs) and the live tools/list of a running BrowserOS neo (25 tools). No personal information — the dataset was screened before training. Task families: inbox triage, unsubscribing, social posting, CRM updates, expense filing with receipt upload, flight search, PDF archiving, settings changes, history reopen, tab groups, saved skills, parallel multi-tab research, two-task sessions, next-call decisions from page snapshots, error recovery, and human-help cases.

Recipe

LoRA (rank 8, alpha 10) via mlx-vlm SFT from the bf16 base, lr 2e-4, batch 4, max seq 2048, 1 epoch (389 iters). Held-out eval: val loss 0.102, token accuracy 97.8%. Adapter fused back into the base, converted to GGUF with llama.cpp's LFM3 converter (vision tower exported as mmproj), quantized to Q8_0. Verified in llama.cpp: loads and emits schema-valid BrowserOS neo tool calls from snapshot prompts.

Files

lfm3-vl-2b-browseragent-1f00-Q8_0.gguf — the language model.
mmproj-lfm3-vl-2b-browseragent-1f00-F16.gguf — the vision projector.

Notes

Converted and verified with current llama.cpp. Note that some bundled llama.cpp builds (e.g. LM Studio's current engine pack) cannot load the lfm3_vl arch yet — use a current llama.cpp build, or LM Studio once its engine adds lfm3_vl support.
Base model: LiquidAI/LFM3-VL-2B (see its card for license terms).

Downloads last month: 133

GGUF

Model size

2B params

Architecture

lfm3

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Duckets/LFM3-VL-2B-BrowserAgent-GGUF

Base model

LiquidAI/LFM3-1.7B-Base

Finetuned

LiquidAI/LFM3-VL-2B

Quantized

(33)

this model