Instructions to use LiquidAI/LFM2.5-24B-A2B-DSpark-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 LiquidAI/LFM2.5-24B-A2B-DSpark-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 LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

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 LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

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 LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

Use Docker

docker model run hf.co/LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

LM Studio
Jan

vLLM

How to use LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2.5-24B-A2B-DSpark-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": "LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

Ollama
How to use LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF with Ollama:
```
ollama run hf.co/LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16
```
Unsloth Desktop

How to use LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

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": "LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16
```

Lemonade

How to use LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

Run and chat with the model

lemonade run user.LFM2.5-24B-A2B-DSpark-GGUF-F16

List all available models

lemonade list

Hermes Agent

How to use LiquidAI/LFM2.5-24B-A2B-DSpark-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 LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

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 LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16

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 "LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16" \
  --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"

Try LFM • Docs • Discord

LFM2.5-24B-A2B-DSpark-GGUF

GGUF version of LiquidAI/LFM2.5-24B-A2B-DSpark for llama.cpp.

This is a standalone draft sidecar: it carries only the drafter (5 attention layers, rank-256 Markov head, confidence head, block size 9). Token embeddings and the LM head are shared from the target model at load time, so it must be paired with a LFM2.5-24B-A2B-GGUF target file.

Find more information about LFM2.5-DSpark in our blog post.

📦 Files

File	Quant	Size
`LFM2.5-24B-A2B-DSpark-F16.gguf`	F16	664 MB

Choose the target quantization from LFM2.5-24B-A2B-GGUF. Target quantization affects acceptance, speed, and output quality.

🏃 How to run (llama.cpp)

llama-server -hf LiquidAI/LFM2.5-24B-A2B-GGUF:F16 \
  -hfd LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF:F16 \
  --spec-type draft-dspark --spec-draft-n-max 9 --spec-draft-n-min 0 \
  -ngl 99 -ngld 99 -fa on

The block size is read from the sidecar metadata, and --spec-draft-n-max is clamped to it. The target verifies proposed tokens. Floating-point effects can produce different text from target-only decoding, including under greedy sampling. Per-response timings report draft_n and draft_n_accepted.

Other models in the LFM2.5-DSpark GGUF family:

Draft (GGUF)	Target (GGUF)
LFM2.5-1.2B-Instruct-DSpark-GGUF	LFM2.5-1.2B-Instruct-GGUF
LFM2.5-2.6B-DSpark-GGUF	LFM2.5-2.6B-GGUF
LFM2.5-VL-3B-DSpark-GGUF	LFM2.5-VL-3B-GGUF
LFM2.5-8B-A1B-DSpark-GGUF	LFM2.5-8B-A1B-GGUF
LFM2.5-24B-A2B-DSpark-GGUF	LFM2.5-24B-A2B-GGUF

📊 Acceptance and benchmarks

See LiquidAI/LFM2.5-24B-A2B-DSpark for model details and SGLang FP8 benchmarks on NVIDIA B300. Those results are not llama.cpp GGUF measurements; GGUF speedup depends on target quantization, hardware, and workload. See LiquidAI/LFM2.5-24B-A2B for target quality benchmarks.

📬 Contact

Got questions or want to connect? Join our Discord community
If you are interested in custom solutions with edge deployment, please contact our sales team.

Citation

@article{liquidAI202624BA2B,
  author  = {Liquid AI},
  title   = {LFM2.5-24B-A2B: Built for Fast On-Device Agents},
  journal = {Liquid AI Blog},
  year    = {2026},
  note    = {www.liquid.ai/blog/lfm2-5-24b-a2b},
}

@article{liquidAI2026dspark,
  author = {Liquid AI},
  title = {LFM2.5-DSpark: Up to 3.2x Faster Inference from H100 to MacBook},
  journal = {Liquid AI Blog},
  year = {2026},
  note = {www.liquid.ai/blog/lfm2.5-dspark},
}

Downloads last month: 945

GGUF

Model size

0.3B params

Architecture

dflash

Hardware compatibility

16-bit

Model tree for LiquidAI/LFM2.5-24B-A2B-DSpark-GGUF

Base model

LiquidAI/LFM2.5-24B-A2B-Base

Finetuned

LiquidAI/LFM2.5-24B-A2B

Finetuned

LiquidAI/LFM2.5-24B-A2B-DSpark

Quantized

(1)

this model