Instructions to use SamanyoluAI/Synapse1.5-1B-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 SamanyoluAI/Synapse1.5-1B-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 SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

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 SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

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 SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

Use Docker

docker model run hf.co/SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use SamanyoluAI/Synapse1.5-1B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SamanyoluAI/Synapse1.5-1B-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": "SamanyoluAI/Synapse1.5-1B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

Ollama
How to use SamanyoluAI/Synapse1.5-1B-GGUF with Ollama:
```
ollama run hf.co/SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0
```
Unsloth Desktop

How to use SamanyoluAI/Synapse1.5-1B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

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": "SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SamanyoluAI/Synapse1.5-1B-GGUF with Docker Model Runner:
```
docker model run hf.co/SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0
```

Lemonade

How to use SamanyoluAI/Synapse1.5-1B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

Run and chat with the model

lemonade run user.Synapse1.5-1B-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use SamanyoluAI/Synapse1.5-1B-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 SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

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 SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SamanyoluAI/Synapse1.5-1B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0

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 "SamanyoluAI/Synapse1.5-1B-GGUF:Q8_0" \
  --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"

Synapse 1.5 1B

Synapse 1.5 is SamanyoluAI's compact edge model — a 1.2B-parameter instruction-tuned LLM packaged in Q8_0 GGUF for local deployment via LM Studio, llama.cpp, and other GGUF runtimes.

Synapse 1.5 is built on LiquidAI/LFM2.5-1.2B-Instruct, released under the LFM Open License v1.0.

Specs


Parameters	1.2B
Quantization	Q8_0
File size	1.25 GB
Context length	128,000
Architecture	`lfm2`
Languages	English, Arabic, Chinese, French, German, Japanese, Korean, Spanish

Usage

LM Studio — search for Synapse1.5-1B-GGUF, or place the .gguf under ~/.lmstudio/models/SamanyoluAI/Synapse1.5-1B-GGUF/.

llama.cpp

llama-cli -m Synapse1.5-1B-Q8_0.gguf -p "Hello"

Python (huggingface_hub)

from huggingface_hub import hf_hub_download

path = hf_hub_download(
    repo_id="SamanyoluAI/Synapse1.5-1B-GGUF",
    filename="Synapse1.5-1B-Q8_0.gguf",
)

Changes from the base model

This release modifies metadata only — the weights are unmodified. The tensor data section is byte-identical to the base model (SHA-256 3402faf5...).

GGUF general.* metadata rebranded: name, basename, size_label, plus added version, organization, description, and license.
Chat template extended with a default Synapse identity, injected only when the caller supplies no system prompt. A caller-provided system prompt overrides it.

Architecture, tokenizer, vocabulary, and all lfm2.* hyperparameters are unchanged.

License

Released under the LFM Open License v1.0, inherited from the base model. Note two conditions carried over from that license:

§5 limits commercial use to entities under $10M USD annual revenue.
§7 grants no trademark rights. This release is not affiliated with or endorsed by Liquid AI, Inc.

Acknowledgements

Base model by Liquid AI. Packaged and released by SamanyoluAI.

Downloads last month: 9

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

8-bit

Model tree for SamanyoluAI/Synapse1.5-1B-GGUF

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-Instruct

Quantized

(126)

this model