Instructions to use AtomicChat/LFM3-VL-2B-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 AtomicChat/LFM3-VL-2B-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 AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/LFM3-VL-2B-GGUF: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 AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/LFM3-VL-2B-GGUF: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 AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use AtomicChat/LFM3-VL-2B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/LFM3-VL-2B-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": "AtomicChat/LFM3-VL-2B-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/AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M

Ollama
How to use AtomicChat/LFM3-VL-2B-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M

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": "AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AtomicChat/LFM3-VL-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM3-VL-2B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AtomicChat/LFM3-VL-2B-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 AtomicChat/LFM3-VL-2B-GGUF: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 AtomicChat/LFM3-VL-2B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

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

LFM3-VL-2B — GGUF (by AtomicChat)

Atomic-Dynamic (AD) GGUF quants of LiquidAI/LFM3-VL-2B, a vision-language model on the LFM3 hybrid (short-convolution + gated attention) backbone.

Per-tensor AD layout by role (FFN pressed by depth band, attn_gate / attn_k/v kept high, short-conv mixers tracked with attention, embeddings and head high).

Rungs (language model)

top-1 is how often the rung picks the same next token as the original BF16 (30-language neutral set); mean KLD is the average divergence from BF16 (lower is better). This is a small hybrid model and is fairly quantization-sensitive.

Rung	GB on disk	bpw	top-1	mean KLD
Q8_0	1.85	8.51	96.6%	0.003
AD-Q6_K	1.59	7.31	94.9%	0.006
AD-Q5_K_M	1.31	6.03	90.7%	0.024
AD-Q4_K_M	1.13	5.20	85.8%	0.061
AD-IQ4_XS	1.09	5.02	83.8%	0.078
AD-IQ3_S	0.92	4.23	78.3%	0.151

AD-Q4_K_M is the recommended default. AD-IQ3_S is a research-grade rung. The AD rungs replace llama.cpp's stock presets (no imatrix) at every size. Full metrics go to the -metrics repo after audit.

Vision

The vision projector is included: mmproj-LFM3-VL-2B-F16.gguf (BF16 also available). Pair it with any rung via llama-mtmd-cli:

llama-mtmd-cli -m LFM3-VL-2B-AD-Q4_K_M.gguf --mmproj mmproj-LFM3-VL-2B-F16.gguf --image img.jpg -p "Describe the image"

Run (llama.cpp, text)

Needs a build with LFM3 support (merged in llama.cpp #31252; produced at llama.cpp 19cce69).

llama-cli -hf AtomicChat/LFM3-VL-2B-GGUF:AD-Q4_K_M -p "Hello"

Base model & license

Base model: LiquidAI/LFM3-VL-2B. License: LFM Open License v1.0 (see LICENSE).

Quants by AtomicChat.

Downloads last month: -

GGUF

Model size

2B params

Architecture

lfm3

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for AtomicChat/LFM3-VL-2B-GGUF

Base model

LiquidAI/LFM3-1.7B-Base

Finetuned

LiquidAI/LFM3-VL-2B

Quantized

(12)

this model

Collection including AtomicChat/LFM3-VL-2B-GGUF

LFM3

Collection

AtomicChat AD GGUF quants of Liquid's LFM3 family. • 2 items • Updated about 2 hours ago