Instructions to use gggff123/lfmCodeEnhanced with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use gggff123/lfmCodeEnhanced 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 gggff123/lfmCodeEnhanced:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gggff123/lfmCodeEnhanced:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf gggff123/lfmCodeEnhanced:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gggff123/lfmCodeEnhanced:Q4_K_M

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 gggff123/lfmCodeEnhanced:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf gggff123/lfmCodeEnhanced:Q4_K_M

Use Docker

docker model run hf.co/gggff123/lfmCodeEnhanced:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use gggff123/lfmCodeEnhanced with Ollama:
```
ollama run hf.co/gggff123/lfmCodeEnhanced:Q4_K_M
```
Unsloth Desktop

How to use gggff123/lfmCodeEnhanced with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gggff123/lfmCodeEnhanced: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": "gggff123/lfmCodeEnhanced:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use gggff123/lfmCodeEnhanced with Docker Model Runner:
```
docker model run hf.co/gggff123/lfmCodeEnhanced:Q4_K_M
```

Lemonade

How to use gggff123/lfmCodeEnhanced with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gggff123/lfmCodeEnhanced:Q4_K_M

Run and chat with the model

lemonade run user.lfmCodeEnhanced-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use gggff123/lfmCodeEnhanced with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gggff123/lfmCodeEnhanced: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 gggff123/lfmCodeEnhanced:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use gggff123/lfmCodeEnhanced with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf gggff123/lfmCodeEnhanced: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 "gggff123/lfmCodeEnhanced: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"

LFM 2.5 230m Code-Enhanced

Lfm 2.5 230m code enhanced is a code-ish version of the previous lfm 2.5 230m (base) , this model however attempts to make the old model better at coding this uses the latest weight space programming paper along with deepseek v4.1 flash to manually change the model weights.

LFM CodeEnhanced AI

LFM CodeEnhanced

AI · CODE · CREATE

Currently has 3 quantizations

Quantization	Quality
BF16	Highest quality Recommended
Q4_KM	Mid Quality
Q8	Also good

This model was generated by deepseek V4.1 FLASH by changing model weights.

All credits to liquid-ai, deepseek & weight space programming research paper

Downloads last month: -

GGUF

Model size

0.2B params

Architecture

lfm2

Hardware compatibility

4-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for gggff123/lfmCodeEnhanced

Base model

LiquidAI/LFM2.5-230M-Base

Finetuned

LiquidAI/LFM2.5-230M

Quantized

(37)

this model