Instructions to use Convergent-ch/Quasar-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Convergent-ch/Quasar-1.0 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 Convergent-ch/Quasar-1.0
# Run inference directly in the terminal:
llama cli -hf Convergent-ch/Quasar-1.0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Convergent-ch/Quasar-1.0
# Run inference directly in the terminal:
llama cli -hf Convergent-ch/Quasar-1.0

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 Convergent-ch/Quasar-1.0
# Run inference directly in the terminal:
./llama-cli -hf Convergent-ch/Quasar-1.0

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 Convergent-ch/Quasar-1.0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Convergent-ch/Quasar-1.0

Use Docker

docker model run hf.co/Convergent-ch/Quasar-1.0

Llama new
LM Studio
Jan

vLLM

How to use Convergent-ch/Quasar-1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Convergent-ch/Quasar-1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Convergent-ch/Quasar-1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Convergent-ch/Quasar-1.0

Ollama
How to use Convergent-ch/Quasar-1.0 with Ollama:
```
ollama run hf.co/Convergent-ch/Quasar-1.0
```
Unsloth Desktop

How to use Convergent-ch/Quasar-1.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Convergent-ch/Quasar-1.0

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": "Convergent-ch/Quasar-1.0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Convergent-ch/Quasar-1.0 with Docker Model Runner:
```
docker model run hf.co/Convergent-ch/Quasar-1.0
```

Lemonade

How to use Convergent-ch/Quasar-1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Convergent-ch/Quasar-1.0

Run and chat with the model

lemonade run user.Quasar-1.0-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Convergent-ch/Quasar-1.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Convergent-ch/Quasar-1.0

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 Convergent-ch/Quasar-1.0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Convergent-ch/Quasar-1.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Convergent-ch/Quasar-1.0

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 "Convergent-ch/Quasar-1.0" \
  --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"

Quasar 1.0

Quasar 1.0 is a small, chill chat assistant made by Convergent. It is a fine-tune of Qwen3.5-0.8B by Alibaba (Apache 2.0); it was not trained from scratch. The fine-tune gives it the Quasar identity and a relaxed, friendly personality in German and English.

Quick start

ollama create quasar-1.0 -f Modelfile
ollama run quasar-1.0

The Modelfile uses Ollama's built-in Qwen3.5 renderer and parser, a short Quasar system prompt and temperature 0.3. GGUF: Q8_0, 812 MB. Only the text part of Qwen3.5 is included (no image input).

Training

LoRA (r 16, alpha 32) on the language-model linear layers, 2 epochs, learning rate 2e-4, loss only on the replies, on one RTX 3060 Ti in about 4 minutes; merged into the weights afterwards.
Data: 763 chats. 463 replies in Quasar's chill style (209 German, 254 English) to everyday prompts from SmolTalk, written by a local Qwen3 8B, plus 300 identity chats ("I'm Quasar from Convergent").

Evaluation

70 small Python tasks with unit tests (temperature 0):

Model	Passed
Qwen3.5-0.8B (base)	60 / 70
Quasar 1.0	61 / 70

The fine-tune did not make coding worse. It is still a 0.8B model: it handles simple functions and short explanations, makes factual mistakes, and at higher temperatures sometimes answers the wrong question (this is why the Modelfile uses 0.3).

License

Apache 2.0, like the base model. Base model: Qwen3.5-0.8B, Copyright Alibaba Cloud.

Downloads last month: 210

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Convergent-ch/Quasar-1.0

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

(370)

this model