Instructions to use batiai/LFM2.5-8B-A1B-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 batiai/LFM2.5-8B-A1B-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 batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf batiai/LFM2.5-8B-A1B-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 batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf batiai/LFM2.5-8B-A1B-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 batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf batiai/LFM2.5-8B-A1B-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 batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use batiai/LFM2.5-8B-A1B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "batiai/LFM2.5-8B-A1B-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": "batiai/LFM2.5-8B-A1B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M

Ollama
How to use batiai/LFM2.5-8B-A1B-GGUF with Ollama:
```
ollama run hf.co/batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf batiai/LFM2.5-8B-A1B-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": "batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use batiai/LFM2.5-8B-A1B-GGUF with Docker Model Runner:
```
docker model run hf.co/batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LFM2.5-8B-A1B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use batiai/LFM2.5-8B-A1B-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 batiai/LFM2.5-8B-A1B-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 batiai/LFM2.5-8B-A1B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

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

Liquid LFM2.5-8B-A1B GGUF — Quantized by BatiAI

Quantizations of Liquid AI LFM2.5-8B-A1B (8.3B total / 1.5B active MoE, reasoning + tool calling) for on-device AI on Mac. Built and verified by BatiAI for BatiFlow.

Why LFM2.5-8B-A1B?

8.3B total, only 1.5B active — MoE (32 experts, 4 active) gives 8B-class quality at ~1.5B-class speed
Hybrid architecture — 24 layers: 18 double-gated LIV convolution + 6 GQA attention. Built for edge, not GPUs
Reasoning model — explicit chain-of-thought before the final answer
Native tool calling — Pythonic or JSON function calls (<|tool_call_start|> / <|tool_call_end|>)
128K context, 38T-token training budget, 128K vocab (better non-Latin tokenization incl. Korean)
Blazing on-device — Liquid reports 253 tok/s on M5 Max, 146 tok/s on Ryzen AI Max+ 395, all under 6GB
Released May 28, 2026

Quick Start

ollama pull batiai/lfm2.5-8b:q4

Available Quantizations

Quant	Size	Recommended For
Q2_K_S	~2.8 GB	8GB Mac, ultra-compact (imatrix)
IQ3_XXS	~3.2 GB	imatrix, smallest K-class footprint
Q3_K_M	~3.9 GB	8GB+ Mac, balanced
IQ4_XS	~4.3 GB	imatrix, best size/quality
Q4_K_M	~4.9 GB	16GB Mac (recommended)
Q6_K	~6.5 GB	near-original quality

Mac note on Q3_K_M: in every model we've benchmarked on Apple Silicon, Q3_K_M generated slower than Q4_K_M despite the smaller file — Granite 4.1 (+27%), Gemma 4 26B (+12%), Qwen3.8‑27B (+18%), Qwen3.6‑27B (+8%), on both M4 Max and M4 mini. Metal's Q3_K path is limited by dequantization compute rather than bandwidth. We have not measured this particular model's Q3/Q4 pair yet, so treat it as a strong prior, not a measurement: if Q4_K_M fits, take it. On CUDA the two are effectively tied, so this applies to Macs only.

Lower quants (IQ3_XXS, Q2_K_S) and imatrix variants are not provided in the official Liquid GGUF repo — BatiAI adds them for 8GB Macs and tighter footprints.

RAM Requirements

This model is tiny in active params — even the largest quant fits comfortably on 16GB. With only 1.5B active params, throughput stays high regardless of quant.

Your Mac RAM	IQ3	Q2	Q3	IQ4	Q4	Q6
8GB	✅	✅	✅	✅	⚠️	❌
16GB	✅	✅	✅	✅	✅ Recommended	✅
24GB+	✅	✅	✅	✅	✅	✅

Why BatiAI Quantization?

	BatiAI	Official Liquid GGUF
Source	Official Liquid weights	Official
Ollama	✅ `batiai/lfm2.5-8b`	❌ HF only
Low quants	✅ IQ3_XXS, Q2_K_S, Q3_K_M	❌ Q4_0 floor
imatrix	✅ IQ variants calibrated	Standard
Tool calling	✅ Verified	—
BatiAI signed	✅ `general.author=BatiAI`	—

Technical Details

Original Model: LiquidAI/LFM2.5-8B-A1B
Architecture: lfm2_moe hybrid — 18 LIV conv + 6 GQA layers, 32 experts / 4 active per token
Parameters: 8.3B total, 1.5B active
Context: 131,072 tokens
Training: 38T tokens
License: LFM Open License v1.0 (Apache-2.0 based; free commercial use under $10M annual revenue)
Quantized with: llama.cpp + imatrix
Quantized by: BatiAI

About BatiFlow

BatiFlow — free, on-device AI automation for Mac. 5MB app, 100% local, unlimited.

License

Quantized from LiquidAI/LFM2.5-8B-A1B. License: LFM Open License v1.0 — see https://www.liquid.ai/lfm-license. Original Liquid AI attribution retained. Free for commercial use by organizations under $10M USD annual revenue; above that threshold, contact Liquid AI.

Benchmarks

Benchmarks pending — measured on target Mac hardware via bench.sh.

Downloads last month: 307

GGUF

Model size

8B params

Architecture

lfm2moe

Hardware compatibility

2-bit

3-bit

4-bit

6-bit

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

Base model

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

Finetuned

LiquidAI/LFM2.5-8B-A1B

Quantized

(92)

this model

Collection including batiai/LFM2.5-8B-A1B-GGUF

🍎 Runs on a 16–32GB Mac — Korean-verified

Collection

Small enough for an ordinary Mac, and each one actually tested in Korean before release. Chat, OCR, speech and embeddings. • 11 items • Updated about 16 hours ago