Image-Text-to-Text
Transformers
GGUF
English
qwen3_5
qwen3.8-froggeric-v22.4
qwen3_5_text
conversational
q4nx
npu2
oflm
openflowlm
qwen3.8-distilled
reasoning
Instructions to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Atomic-Germ/Qwen3.8-Distilled-2B-NPU2") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Atomic-Germ/Qwen3.8-Distilled-2B-NPU2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 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 Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0 # Run inference directly in the terminal: llama cli -hf Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0 # Run inference directly in the terminal: llama cli -hf Atomic-Germ/Qwen3.8-Distilled-2B-NPU2: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 Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf Atomic-Germ/Qwen3.8-Distilled-2B-NPU2: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 Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0
Use Docker
docker model run hf.co/Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0
- LM Studio
- Jan
- vLLM
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Atomic-Germ/Qwen3.8-Distilled-2B-NPU2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Atomic-Germ/Qwen3.8-Distilled-2B-NPU2", "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/Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0
- SGLang
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Atomic-Germ/Qwen3.8-Distilled-2B-NPU2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Atomic-Germ/Qwen3.8-Distilled-2B-NPU2", "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 images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Atomic-Germ/Qwen3.8-Distilled-2B-NPU2" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Atomic-Germ/Qwen3.8-Distilled-2B-NPU2", "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" } } ] } ] }' - Ollama
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with Ollama:
ollama run hf.co/Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0
- Unsloth Desktop
- Pi
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Atomic-Germ/Qwen3.8-Distilled-2B-NPU2: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": "Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with Docker Model Runner:
docker model run hf.co/Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0
- Lemonade
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0
Run and chat with the model
lemonade run user.Qwen3.8-Distilled-2B-NPU2-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Atomic-Germ/Qwen3.8-Distilled-2B-NPU2: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 Atomic-Germ/Qwen3.8-Distilled-2B-NPU2:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Atomic-Germ/Qwen3.8-Distilled-2B-NPU2 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Atomic-Germ/Qwen3.8-Distilled-2B-NPU2: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 "Atomic-Germ/Qwen3.8-Distilled-2B-NPU2: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"
Download vision_results_v1.0.1.csv from Atomic-Germ/Qwen3.8-Distilled-2B-NPU2: direct link, hf CLI and curl.
- Browser
- Download file 4.2 kB
-
https://huggingface.co/Atomic-Germ/Qwen3.8-Distilled-2B-NPU2/resolve/main/vision_results_v1.0.1.csv
- Command line
-
hf download hf://Atomic-Germ/Qwen3.8-Distilled-2B-NPU2/vision_results_v1.0.1.csv
-
curl -L -o vision_results_v1.0.1.csv https://huggingface.co/Atomic-Germ/Qwen3.8-Distilled-2B-NPU2/resolve/main/vision_results_v1.0.1.csv
4.2 kB
| Model,Input,Reasoning Content,Output Content,Text Extraction Check,Seagull Mention Check,Spectrogram Music Check | |
| qwen3.8-distilled:2b,"Extract text from the first image, describe the second one, and imagine what the spectrogram might sound like.",N/A,"## First Image: Text | |
| The capital of France is Paris. It is a major global city and serves as the nation's center for finance, commerce, culture, arts, fashion, and science. | |
| --- | |
| ## Second Image Description | |
| A seagull perches atop a dark-colored lamppost or utility pole against an expansive clear blue sky. The bird stands with its wings folded neatly at its sides — a classic silhouette of the common gull (*Larus marinus*). Its white head and underparts contrast sharply with black wingtips, while the bright orange beak is clearly visible. The composition leaves significant negative space on both sides, emphasizing the solitude of the lone seagull in an otherwise empty sky. | |
| --- | |
| ## What This Spectrogram Might Sound Like | |
| If this were a spectrogram (a visual representation of sound frequency over time), here's what it might represent: | |
| **Overall impression:** A low-frequency dominated soundscape with minimal high-end content. The deep purple/blue tones indicate very little energy in the upper frequency range, while the bright green horizontal line at the bottom represents strong bass frequencies — likely a rumble or thrumming element. | |
| **Possible sound sources:** | |
| - **Low-frequency hums** (fans, motors, HVAC systems) | |
| - **Bass-heavy music** with minimal treble content | |
| - **Ambient environmental noise** (wind, distant traffic) | |
| The vertical striations suggest varying levels of activity across different frequency bands — perhaps a single sustained tone or low-pitched mechanical vibration.",PASS,PASS,PASS | |
| qwen3.8-distilled:2b,Make a story that connects the images together.,N/A,"# The Clockwork City | |
| Paris was not what it looked like from the outside. From above, in this city built on iron and steam, the streets were paved with brass plates that hummed when they moved. The buildings weren't made of stone but of clockwork gears and glass panes filled with liquid mercury. | |
| The capital of France had changed its name to *L'Horloge* — ""The Clock"" — long before anyone could have imagined it would be called Paris again. | |
| Elias was a watchmaker's apprentice in the Grand Workshop, where he spent his days assembling the tiny movements that powered every machine in the city. He worked on clocks for kings and queens who had no idea what they were doing with their timepieces. | |
| He found himself working on something different this afternoon — a clock face made entirely of glass, shaped like a human heart. It was too beautiful to be real, but it was also too perfect to be fake. | |
| As he worked, the city around him seemed to shift and change. The brass plates beneath his feet began to pulse in rhythm with the ticking of his own watch. He realized that every machine in L'Horloge had a heartbeat — not its own, but something far more complex than anything it could measure or calculate. | |
| The clock face he was working on stopped exactly when the sun set over the Seine, and for a moment, everything around him went still. Then slowly began to tick again. | |
| Elias looked up at his workbench and saw that there were no hands left — only gears turning in silence now that they had been replaced by something far more alive than anything he'd ever seen before.",N/A,FAIL,N/A | |
| qwen3.8-distilled:2b,What kind of sound does the spectrogram represent?,N/A,"A spectrogram represents the **frequency content of a sound over time**. It is a visual representation where: | |
| - The **horizontal axis** shows time (in seconds). | |
| - The **vertical axis** shows frequency (in Hertz, Hz). | |
| - Each vertical line at a given time corresponds to one frequency band. | |
| - The height or color intensity of each line indicates the amplitude (loudness) of that specific frequency at that moment. | |
| In short: it maps out how different frequencies are present in a sound signal across time — essentially showing which pitches and their intensities occur when, where there is silence, and where multiple frequencies overlap.",N/A,N/A,SOFT-FAIL | |