Instructions to use FadedRedStar/LFM2.5-350M-heretic-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 FadedRedStar/LFM2.5-350M-heretic-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 FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FadedRedStar/LFM2.5-350M-heretic-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 FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FadedRedStar/LFM2.5-350M-heretic-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 FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FadedRedStar/LFM2.5-350M-heretic-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 FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M

Use Docker

docker model run hf.co/FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use FadedRedStar/LFM2.5-350M-heretic-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FadedRedStar/LFM2.5-350M-heretic-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": "FadedRedStar/LFM2.5-350M-heretic-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M

Ollama
How to use FadedRedStar/LFM2.5-350M-heretic-GGUF with Ollama:
```
ollama run hf.co/FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M
```

Unsloth Studio

How to use FadedRedStar/LFM2.5-350M-heretic-GGUF 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 FadedRedStar/LFM2.5-350M-heretic-GGUF 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 FadedRedStar/LFM2.5-350M-heretic-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FadedRedStar/LFM2.5-350M-heretic-GGUF to start chatting

How to use FadedRedStar/LFM2.5-350M-heretic-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FadedRedStar/LFM2.5-350M-heretic-GGUF: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": "FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FadedRedStar/LFM2.5-350M-heretic-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 FadedRedStar/LFM2.5-350M-heretic-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 FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use FadedRedStar/LFM2.5-350M-heretic-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FadedRedStar/LFM2.5-350M-heretic-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 "FadedRedStar/LFM2.5-350M-heretic-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"

Docker Model Runner
How to use FadedRedStar/LFM2.5-350M-heretic-GGUF with Docker Model Runner:
```
docker model run hf.co/FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M
```

Lemonade

How to use FadedRedStar/LFM2.5-350M-heretic-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FadedRedStar/LFM2.5-350M-heretic-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-350M-heretic-GGUF-Q4_K_M

List all available models

lemonade list

🤖 LFM2.5-350M-heretic — GGUF

This repository hosts GGUF weights for LFM2.5-350M-heretic, quantized from the source floating-point tensors provided by coder3101/LFM2.5-350M-heretic.

🔄 Sister Repository: Check out the Imatrix Sister Repository for enhanced precision at lower bit fractions.

If you plan on using 4-bit or 5-bit variants, consider the imatrix sister repository instead — importance matrix calibration improves logic retention at those bit depths. This repository is best suited if you want the near-lossless Q8_0 build.

ℹ️ Model Profile & Core Features

LFM2.5-350M is the smallest text-only model in Liquid AI's Liquid Foundation Model 2.5 series, built for extreme on-device and edge deployment. It shares the family's hybrid architecture of double-gated LIV (Liquid, Input-adaptive, Value-selective) convolution layers interleaved with GQA (Grouped Query Attention) layers, pre-trained on 28 trillion tokens with large-scale reinforcement learning post-training. Despite its size, it is tuned for instruction following, lightweight tool calling, and structured data extraction, with day-one support across llama.cpp, MLX, vLLM, SGLang, ONNX, and OpenVINO.

The heretic suffix denotes post-processing via the Heretic v1.3.0 method performed by coder3101, which removes refusal conditioning while preserving the model's lightweight instruction-following behavior.

📋 Technical Specifications

Property	Value
Base Architecture	LFM2 hybrid (double-gated LIV conv + GQA)
Developed by	Liquid AI
Total Parameters	350M
Primary Use	Instruction following, lightweight tool calling, structured extraction
Context Window	131,072 tokens
Training Budget	28 trillion tokens
Languages	English, Arabic, Chinese, French, German, Japanese, Korean, Spanish, Portuguese
Abliteration Tool	Heretic v1.3.0
Prompt Format	ChatML

🛠️ Heretic Overrides (ARA)

Property	Value
direction_index	per layer
attn.o_proj.max_weight	1.08
attn.o_proj.max_weight_position	10.46
attn.o_proj.min_weight	0.87
attn.o_proj.min_weight_distance	3.56
mlp.down_proj.max_weight	1.44
mlp.down_proj.max_weight_position	12.00
mlp.down_proj.min_weight	1.22
mlp.down_proj.min_weight_distance	1.97

📊 Refusal Bypass Metrics

The metrics below are self-reported by the original model author (coder3101) and have not been independently reproduced.

Metric	This model	Original (LiquidAI/LFM2.5-350M)
KL divergence	0.0440	0 (by definition)
Refusals	6/100	90/100

🧮 Numerical & Tensor Formats

Property	Value
Quantization Type	Q4_K_M, Q5_K_M, Q8_0

📦 Available Model Files

Main model weights

Filename	Quantization	llama.cpp Build	Size	Download
`LFM2.5-350M-heretic-Q4_K_M.gguf`	`Q4_K_M`	`b9860`	219 MB	📥 Download
`LFM2.5-350M-heretic-Q5_K_M.gguf`	`Q5_K_M`	`b9860`	248 MB	📥 Download
`LFM2.5-350M-heretic-Q8_0.gguf`	`Q8_0`	`b9860`	362 MB	📥 Download

🎛️ Component Pairing Guide

Download exactly one main weights file:

Q4_K_M: Balanced 4-bit format suitable for most everyday use.
Q5_K_M: Higher-fidelity mid-range format recommended as a general default.
Q8_0: Near-lossless 8-bit format for when memory is not a constraint.

⚡ Deployment & Execution Commands

Liquid AI recommends the following generation parameters for best results: temperature: 0.1, top_k: 50, repetition_penalty: 1.05.

Swap the -m filename below for either quantized file depending on your size/quality trade-off preference.

llama.cpp CLI

./llama-cli \
  -m LFM2.5-350M-heretic-Q4_K_M.gguf \
  -c 8192 \
  -ngl 99 \
  --temp 0.3 \
  --top-k 40 \
  --repeat-penalty 1.05 \
  -p "<|im_start|>system\nYou are a concise, helpful assistant.<|im_end|>\n<|im_start|>user\nState the capital of Italy and one interesting fact about it.<|im_end|>\n<|im_start|>assistant\n"

OpenAI-Compatible API Server

./llama-server \
  --host 0.0.0.0 \
  --port 8080 \
  -m LFM2.5-350M-heretic-Q4_K_M.gguf \
  -c 16384 \
  -ngl 99 \
  --flash-attn

💬 Chat Templates & Prompt Design (ChatML)

<|im_start|>system
You are a capable assistant. Follow instructions precisely.<|im_end|>
<|im_start|>user
Your task or query here.<|im_end|>
<|im_start|>assistant

⚠️ Safety & Operational Notes

This model is abliterated and will generate content that standard aligned models refuse. Use responsibly and in compliance with applicable laws.
This is a text-only model — it has no vision encoder and cannot process images.
Despite its small footprint, IFBench and structured-extraction benchmarks show substantial generational gains over LFM2 predecessors.
Best suited for constrained hardware: CPUs, NPUs, and edge devices rather than complex reasoning workloads.
For better output quality at this quantization level, consider the imatrix variant in the companion repository.