Instructions to use ggml-org-dev/tinyLFM3-Omni-for-testing-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 ggml-org-dev/tinyLFM3-Omni-for-testing-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 ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K
# Run inference directly in the terminal:
llama cli -hf ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K
# Run inference directly in the terminal:
llama cli -hf ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

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 ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K
# Run inference directly in the terminal:
./build/bin/llama cli -hf ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

Use Docker

docker model run hf.co/ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

Llama new
LM Studio
Jan
Ollama
How to use ggml-org-dev/tinyLFM3-Omni-for-testing-gguf with Ollama:
```
ollama run hf.co/ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K
```
Unsloth Desktop

How to use ggml-org-dev/tinyLFM3-Omni-for-testing-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

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": "ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ggml-org-dev/tinyLFM3-Omni-for-testing-gguf with Docker Model Runner:
```
docker model run hf.co/ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K
```

Lemonade

How to use ggml-org-dev/tinyLFM3-Omni-for-testing-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

Run and chat with the model

lemonade run user.tinyLFM3-Omni-for-testing-gguf-Q2_K

List all available models

lemonade list

Hermes Agent

How to use ggml-org-dev/tinyLFM3-Omni-for-testing-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 ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

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 ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ggml-org-dev/tinyLFM3-Omni-for-testing-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K

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 "ggml-org-dev/tinyLFM3-Omni-for-testing-gguf:Q2_K" \
  --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"

tinyLFM3-Omni-for-testing

This is a modified, damaged copy of LiquidAI/LFM3-Omni-2B, made only to test software. Its output is gibberish. Do not use it for anything else.

It keeps the architecture of LFM3-Omni, so it runs the same code paths as the real model in llama.cpp (TTS, ASR, realtime audio and image input), but it is small enough for CI.

Use the real model instead: https://huggingface.co/ggml-org/LFM3-Omni-2B-GGUF

Changes from the original model

Sliced from the safetensors with slice_lfm3omni.py, which follows the slice-model skill of llama.cpp, then converted with convert_hf_to_gguf.py:

Text model: 4 of 24 layers (0, 2, 3, 4), hidden size 2048 -> 256, heads 16 -> 2, KV heads 4 -> 1, FFN 7680 -> 256
Audio encoder: 3 of 17 layers (0, 2, 3), FFN 1792 -> 256
Depthformer: 1 of 3 layers, hidden size 1024 -> 128, heads 32 -> 4, KV heads 8 -> 1, FFN 2816 -> 256
Audio codec: all 8 layers (the loader requires it), FFN 2304 -> 256
Vision encoder: 2 of 14 layers (0, 2), hidden size 1024 -> 256, heads 16 -> 4, KV heads 8 -> 2, FFN 2560 -> 256, projector 4096 -> 256

Then finish_gguf.py made these changes:

Weights quantized to Q2_K, Q4_K and Q4_0
Added the asr chat template of LFM3-Audio, which the original model does not have. This enables the live transcription path (/v1/realtime?intent=transcription) for testing

License

Derived from LFM3-Omni-2B by Liquid AI, under the LFM Open License v1.0.

Downloads last month: 2,311

GGUF

Model size

34.5M params

Architecture

lfm3

Hardware compatibility

2-bit

Inference Providers NEW

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