Instructions to use Solel-io/Seraphim-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Solel-io/Seraphim-1 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 Solel-io/Seraphim-1:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Solel-io/Seraphim-1:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Solel-io/Seraphim-1:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf Solel-io/Seraphim-1:IQ4_XS

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 Solel-io/Seraphim-1:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf Solel-io/Seraphim-1:IQ4_XS

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 Solel-io/Seraphim-1:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Solel-io/Seraphim-1:IQ4_XS

Use Docker

docker model run hf.co/Solel-io/Seraphim-1:IQ4_XS

LM Studio
Jan

vLLM

How to use Solel-io/Seraphim-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Solel-io/Seraphim-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Solel-io/Seraphim-1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Solel-io/Seraphim-1:IQ4_XS

Ollama
How to use Solel-io/Seraphim-1 with Ollama:
```
ollama run hf.co/Solel-io/Seraphim-1:IQ4_XS
```
Unsloth Desktop

How to use Solel-io/Seraphim-1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Solel-io/Seraphim-1:IQ4_XS

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": "Solel-io/Seraphim-1:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Solel-io/Seraphim-1 with Docker Model Runner:
```
docker model run hf.co/Solel-io/Seraphim-1:IQ4_XS
```

Lemonade

How to use Solel-io/Seraphim-1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Solel-io/Seraphim-1:IQ4_XS

Run and chat with the model

lemonade run user.Seraphim-1-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use Solel-io/Seraphim-1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Solel-io/Seraphim-1:IQ4_XS

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 Solel-io/Seraphim-1:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Solel-io/Seraphim-1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Solel-io/Seraphim-1:IQ4_XS

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 "Solel-io/Seraphim-1:IQ4_XS" \
  --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"

Aether Series by Solel//ai

Seraphim-1

Seraphim is the flagship. It's the largest model in the Aether Series from Solel//ai, and the most capable one we make, sized to fit a single consumer graphics card at home.

Seraphim reads images as well as text. Give it a photo, a screenshot or a scanned page and ask about it.

All sunshine. No cloud.

At a glance


Family	Aether Series by Solel//ai
Role	Flagship
Parameters	About 27.8 billion (language model plus vision encoder)
Built on	Qwen3.5-27B (Apache-2.0)
Input	Text and images
Output	Text
Context window	Up to 262,144 tokens (in practice, set by your memory)
Format	GGUF, IQ4_XS quantisation, with an f16 vision projector
Licence	Solel model licence v1.1, open weights

Files

File	Size	What it is
`Seraphim-1.IQ4_XS.gguf`	14.80 GB	The model weights
`Seraphim-1.mmproj-f16.gguf`	0.93 GB	The vision projector, needed for images
`chat_template.jinja`, `tokenizer.json`, `config.json` and friends	small	Template, tokeniser and config

Hardware

About 15.7 GB of files in total. A 24 GB graphics card is the comfortable fit, with room for long contexts. A 16 GB card will load it, but only with a short context or some layers offloaded to the CPU.

Run it

In Solel//os

Pick Seraphim from the Models page and Solel//os downloads it for you if your hardware can take it.

With llama.cpp

llama-server -m Seraphim-1.IQ4_XS.gguf --mmproj Seraphim-1.mmproj-f16.gguf

Then point any OpenAI-compatible client at the server and attach images to your messages.

Good at, and not so good at

Seraphim is for the harder jobs: longer reasoning, careful writing, detailed image and document understanding, and work where Angel or Dominion run out of depth. It's slower and needs more memory than the others, and like every language model it can be confidently wrong. Check anything that matters.

Content and safety

Seraphim has lighter refusal behaviour than its base model. It's meant for adults running it on their own hardware. If you put it in front of other people, add your own filtering. You're responsible for how you use it and what you do with its output.

Licence

Seraphim-1 is open weights under the Solel model licence v1.1. It's free for personal use, research and teaching, and for organisations with annual revenue at or below US$1 million. Above that, you'll need a commercial licence (not offered yet; email legal@solel.io). Because of that threshold it isn't open source, and we don't call it that. The licence also sets out acceptable use rules that pass on to anyone you share it with.

It's built on Qwen3.5-27B by the Qwen team, released under Apache-2.0; that licence and its notices are kept with these files.

If you share a fine-tune or other derivative, include this notice: "Built on Seraphim from the Aether Series by Solel//io, used under the Solel model licence v1.1."

The names Solel, Solel//ai, Aether Series and Seraphim are trade marks of Solel//io. The licence covers the weights, not the names. See the Solel//io trade mark policy.

About Solel//ai

solel//ai

Solel//ai is the AI division of Solel//io, an Australian open-source home server business. We make local models that run on hardware you own, so your conversations stay in your house.

Angel: fast
Dominion: everyday
Seraphim: flagship

Downloads last month: 71

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for Solel-io/Seraphim-1

Base model

Qwen/Qwen3.5-27B

Finetuned

(340)

this model

Collection including Solel-io/Seraphim-1

The Aether Series

Collection

3 items • Updated 1 day ago