Instructions to use mudler/LFM2.5-8B-A1B-APEX-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 mudler/LFM2.5-8B-A1B-APEX-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 mudler/LFM2.5-8B-A1B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf mudler/LFM2.5-8B-A1B-APEX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mudler/LFM2.5-8B-A1B-APEX-GGUF
# Run inference directly in the terminal:
llama cli -hf mudler/LFM2.5-8B-A1B-APEX-GGUF

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 mudler/LFM2.5-8B-A1B-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf mudler/LFM2.5-8B-A1B-APEX-GGUF

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 mudler/LFM2.5-8B-A1B-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mudler/LFM2.5-8B-A1B-APEX-GGUF

Use Docker

docker model run hf.co/mudler/LFM2.5-8B-A1B-APEX-GGUF

LM Studio
Jan
Ollama
How to use mudler/LFM2.5-8B-A1B-APEX-GGUF with Ollama:
```
ollama run hf.co/mudler/LFM2.5-8B-A1B-APEX-GGUF
```

Unsloth Studio

How to use mudler/LFM2.5-8B-A1B-APEX-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 mudler/LFM2.5-8B-A1B-APEX-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 mudler/LFM2.5-8B-A1B-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mudler/LFM2.5-8B-A1B-APEX-GGUF to start chatting

How to use mudler/LFM2.5-8B-A1B-APEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mudler/LFM2.5-8B-A1B-APEX-GGUF

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": "mudler/LFM2.5-8B-A1B-APEX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mudler/LFM2.5-8B-A1B-APEX-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 mudler/LFM2.5-8B-A1B-APEX-GGUF

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 mudler/LFM2.5-8B-A1B-APEX-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use mudler/LFM2.5-8B-A1B-APEX-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mudler/LFM2.5-8B-A1B-APEX-GGUF

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 "mudler/LFM2.5-8B-A1B-APEX-GGUF" \
  --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 mudler/LFM2.5-8B-A1B-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/mudler/LFM2.5-8B-A1B-APEX-GGUF
```

Lemonade

How to use mudler/LFM2.5-8B-A1B-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mudler/LFM2.5-8B-A1B-APEX-GGUF

Run and chat with the model

lemonade run user.LFM2.5-8B-A1B-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

LFM2.5-8B-A1B APEX GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of LiquidAI/LFM2.5-8B-A1B.

Brought to you by the LocalAI team | APEX Project

Available Files

File	Profile	Size	Best For
LFM2.5-8B-A1B-APEX-I-Quality.gguf	I-Quality	6.1 GB	Highest quality with imatrix
LFM2.5-8B-A1B-APEX-Quality.gguf	Quality	6.1 GB	Highest quality standard
LFM2.5-8B-A1B-APEX-I-Balanced.gguf	I-Balanced	6.3 GB	Best overall quality/size ratio
LFM2.5-8B-A1B-APEX-Balanced.gguf	Balanced	6.3 GB	General purpose
LFM2.5-8B-A1B-APEX-I-Compact.gguf	I-Compact	4.2 GB	Consumer GPUs, best quality/size
LFM2.5-8B-A1B-APEX-Compact.gguf	Compact	4.2 GB	Consumer GPUs
LFM2.5-8B-A1B-APEX-I-Mini.gguf	I-Mini	3.6 GB	Smallest viable, fastest inference

(I-variants use imatrix-calibrated quantization; the matching base profiles are the same size without imatrix weighting.)

What is APEX?

APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention, token-mixing) and applies a layer-wise precision gradient — edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, multilingual, Wikipedia).

For this hybrid architecture, APEX additionally:

Applies the edge gradient to the routed experts (the dominant parameter cost).
Treats the short-convolution token-mixing tensors (shortconv.in_proj/out_proj) like attention — keeping the per-layer attention precision rather than the flat fallback.
Keeps the 2 leading dense FFN layers at edge (shared) precision.

See the APEX project for full details.

Architecture

Base Model: LiquidAI/LFM2.5-8B-A1B
Architecture: lfm2_moe — hybrid short-convolution + attention MoE
Layers: 24 (2 leading dense + 22 MoE)
Layer mix: 18 short-convolution + 6 full-attention layers
Experts: 32 routed (4 active per token)
Total Parameters: ~8B
Active Parameters: ~1B per token

Run with LocalAI

local-ai run mudler/LFM2.5-8B-A1B-APEX-GGUF@LFM2.5-8B-A1B-APEX-I-Balanced.gguf

Credits

APEX is brought to you by the LocalAI team. Developed through human-driven, AI-assisted research. Built on llama.cpp.

Downloads last month: 4,365

GGUF

Model size

8B params

Architecture

lfm2moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for mudler/LFM2.5-8B-A1B-APEX-GGUF

Base model

LiquidAI/LFM2.5-8B-A1B-Base

Finetuned

LiquidAI/LFM2.5-8B-A1B

Quantized

(59)

this model

Collection including mudler/LFM2.5-8B-A1B-APEX-GGUF

APEX Quants (GGUF)

Collection

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 44 items • Updated 6 days ago • 129