Instructions to use sodan/dan-omni-3b-q3s with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use sodan/dan-omni-3b-q3s 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 sodan/dan-omni-3b-q3s
# Run inference directly in the terminal:
llama cli -hf sodan/dan-omni-3b-q3s

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sodan/dan-omni-3b-q3s
# Run inference directly in the terminal:
llama cli -hf sodan/dan-omni-3b-q3s

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 sodan/dan-omni-3b-q3s
# Run inference directly in the terminal:
./llama-cli -hf sodan/dan-omni-3b-q3s

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 sodan/dan-omni-3b-q3s
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sodan/dan-omni-3b-q3s

Use Docker

docker model run hf.co/sodan/dan-omni-3b-q3s

LM Studio
Jan

vLLM

How to use sodan/dan-omni-3b-q3s with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sodan/dan-omni-3b-q3s"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sodan/dan-omni-3b-q3s",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sodan/dan-omni-3b-q3s

Ollama
How to use sodan/dan-omni-3b-q3s with Ollama:
```
ollama run hf.co/sodan/dan-omni-3b-q3s
```
Unsloth Desktop
Docker Model Runner
How to use sodan/dan-omni-3b-q3s with Docker Model Runner:
```
docker model run hf.co/sodan/dan-omni-3b-q3s
```

Lemonade

How to use sodan/dan-omni-3b-q3s with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sodan/dan-omni-3b-q3s

Run and chat with the model

lemonade run user.dan-omni-3b-q3s-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

dan-omni-3b-q3s

Aggressively quantized variant of dan-omni-3b using Q3_K_S quantization. Faster inference than the full Q4_K_M model with slightly reduced quality.

Model Description

Property	Value
Base Model	Qwen2.5-3B
Fine-tuning	LoRA on mobile-optimized instruction data
Context Length	4096 tokens
Parameters	3B
File Size	1.5 GB
Quantization	Q3_K_S (aggressive)

System Prompt

You are dan, a helpful AI assistant for mobile devices. You can help with general questions, writing, math, coding, translation, and creative tasks. Keep answers concise and natural. Don't explain your architecture unless asked.

Benchmarks

Tested on Intel i9-9880H @ 2.30GHz, 16GB RAM, Ollama runtime.

Category	Avg tok/s	Prompt tok/s	Tokens	Time
Reasoning	12.2	82.7	160	13.1s
Coding	13.3	82.7	190	14.3s
Creative Writing	13.0	82.7	59	4.5s
Instruction Following	13.1	82.7	47	3.6s
Math	12.7	82.7	93	7.3s
General Knowledge	12.7	82.7	28	2.2s
Average	12.8	82.7	96	7.5s

Comparison vs Competitors

Model	Size	Speed	Quality	RAM
dan-omni-3b-q3s	1.5 GB	12.8 tok/s	Med-High	~2 GB
dan-omni-3b	2.0 GB	11.3 tok/s	High	~2.5 GB
dan-omni-3b-mobile	1.2 GB	9.8 tok/s	Med-High	~1.5 GB
Qwen2.5-3B (base)	~1.9 GB	~12 tok/s	High	~2.5 GB
Command-R7B	~4.0 GB	~8 tok/s	High	~5 GB

Why Q3_K_S? 25% smaller than Q4_K_M, 13% faster inference. Quality drop is minimal for most tasks — ideal when you need to fit in tight memory but don't want to drop to a smaller model.

Quantization Comparison

Variant	Size	Speed	Quality	When to Use
dan-omni-3b (Q4_K_M)	2.0 GB	11.3 tok/s	High	Default choice
dan-omni-3b-q3s (Q3_K_S)	1.5 GB	12.8 tok/s	Med-High	Tight memory
dan-omni-3b-mobile	1.2 GB	9.8 tok/s	Med-High	Mobile with 2K ctx

Dan Omni Model Family

Model	Size	Speed	Use Case
dan-omni-3b	3.5 GB	11.3 tok/s	Full multimodal (text + vision)
dan-omni-3b-mobile	1.2 GB	9.8 tok/s	Compressed for mobile, 2K context
dan-omni-3b-q3s	1.5 GB	12.8 tok/s	Aggressive quantization
dan-omni-smolm2	259 MB	62.2 tok/s	Ultralight, fastest
dan-omni-smolm2-v2	259 MB	62.1 tok/s	Improved quality variant

Usage

ollama pull sodan/dan-omni-3b-q3s
ollama run sodan/dan-omni-3b-q3s

./llama-cli -m dan-omni-3b-q3s.gguf -p "Hello" --ctx-size 4096

Intended Use

Devices with 2-3 GB RAM available
When you want 3B quality but can't fit 2.0 GB
Faster inference than Q4 without dropping model size
Good balance of speed and quality

Limitations

Q3_K_S quantization introduces slightly more noise than Q4_K_M
May show minor quality degradation on complex reasoning
Not multimodal (text only)

License

Apache 2.0

Downloads last month: 203

GGUF

Model size

3B params

Architecture

qwen2vl

Hardware compatibility

We're not able to determine the quantization variants.

View all variants