Instructions to use LucidityAI/Synth-2.5-Flash-Preview-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 LucidityAI/Synth-2.5-Flash-Preview-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 LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf LucidityAI/Synth-2.5-Flash-Preview-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 LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf LucidityAI/Synth-2.5-Flash-Preview-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 LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0

Use Docker

docker model run hf.co/LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use LucidityAI/Synth-2.5-Flash-Preview-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LucidityAI/Synth-2.5-Flash-Preview-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": "LucidityAI/Synth-2.5-Flash-Preview-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0

Ollama
How to use LucidityAI/Synth-2.5-Flash-Preview-GGUF with Ollama:
```
ollama run hf.co/LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0
```

Unsloth Studio

How to use LucidityAI/Synth-2.5-Flash-Preview-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 LucidityAI/Synth-2.5-Flash-Preview-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 LucidityAI/Synth-2.5-Flash-Preview-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LucidityAI/Synth-2.5-Flash-Preview-GGUF to start chatting

How to use LucidityAI/Synth-2.5-Flash-Preview-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LucidityAI/Synth-2.5-Flash-Preview-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": "LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use LucidityAI/Synth-2.5-Flash-Preview-GGUF with Docker Model Runner:
```
docker model run hf.co/LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0
```

Lemonade

How to use LucidityAI/Synth-2.5-Flash-Preview-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0

Run and chat with the model

lemonade run user.Synth-2.5-Flash-Preview-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use LucidityAI/Synth-2.5-Flash-Preview-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 LucidityAI/Synth-2.5-Flash-Preview-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 LucidityAI/Synth-2.5-Flash-Preview-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LucidityAI/Synth-2.5-Flash-Preview-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LucidityAI/Synth-2.5-Flash-Preview-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 "LucidityAI/Synth-2.5-Flash-Preview-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"

Synth 2.5 Flash Preview

This is a preview model, it may deliver performance below that of the final model.
This preview is a model finetuned with purely SFT, RLAIF has not been applied yet.
Alongside this, creative performance is currently best on non-thinking mode for this preview.

Synth 2.5 is the next model in the Synth line-up, based on Ling 3 Tiny, it has 8B total parameters and 1B active parameters.

Compared to Synth 2

Compared to Synth 2, 2.5 has the following changes/improvements:

Trained on real-world creative data/usage from SOTA models (and past-sota, user-perferred models)
Optimized for following user-wanted qualities (described here) via RLAIF (READ NOTE FOR PREVIEW)
Hybrid reasoning support, for optional further in-depth creative reasoning

Usage

Composite and LuciditySH Platform

You can test Synth 2.5 Flash at Composite (creative specific) or LuciditySH Platform (coming soon) for free, with up to 100 free requests a day for easy testing/usage.

Local

You can use Synth 2.5 Flash on Llama.cpp (1.0.10481) or VLLM (InclusionAI's Ling 3 fork)

Generation Parameters

It is recommended to use Synth 2.5 Flash with the following generation settings:

Temperature: 0.8-1
Top-P: 0.95
Top-K: 0

Training

For the SFT stage of Synth 2.5's training, it was trained on a closed dataset comprised of real-world creative interactions with the following models, with the amount of interactions:

Family	Samples
Gemini (2.5 Pro)	1
Gemini (3.X Pro/3.7)	1
DeepSeek (V3 0324)	5
DeepSeek (R1 0528)	8
DeepSeek (V4 Pro)	804
GLM (5.X)	1981
GLM (4.X)	58
Kimi (k2.X)	284
Kimi (k3)	3
Minimax M3	69
StepFun	40
total	3254

For model replication, close data to our closed dataset can be found in our PIPKIN datasets.

Limitations (for Preview)

As per the active parameter count of this model (1B) and the fact that it is only in preview, it comes with the following limitations, as flagged by Composite users:

Synth 2.5 Flash Preview is incapable of following deep prompts that require heavy, specific formatting
Synth 2.5 Flash Preview has been noted by users to occasionally write for them, a disruptive quality

Considerations

Synth 2.5 Flash is capable of generating content that is harmful, illegal and/or generally NSFW, as with any LLM. It is recommended to put Synth 2.5 behind a moderation model or other safety layer for real world deployment.

Downloads last month: 79

GGUF

Model size

8B params

Architecture

bailingmoe3

Hardware compatibility

8-bit

Collection including LucidityAI/Synth-2.5-Flash-Preview-GGUF

Synth 2.5 Preview

Collection

Preview versions of the Synth 2.5 family • 2 items • Updated 3 days ago