Instructions to use AllSpark-Research/Iris-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AllSpark-Research/Iris-mini with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AllSpark-Research/Iris-mini")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("AllSpark-Research/Iris-mini")
model = AutoModelForMultimodalLM.from_pretrained("AllSpark-Research/Iris-mini", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AllSpark-Research/Iris-mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AllSpark-Research/Iris-mini

SGLang

How to use AllSpark-Research/Iris-mini 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 "AllSpark-Research/Iris-mini" \
    --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": "AllSpark-Research/Iris-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "AllSpark-Research/Iris-mini" \
        --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": "AllSpark-Research/Iris-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AllSpark-Research/Iris-mini with Docker Model Runner:
```
docker model run hf.co/AllSpark-Research/Iris-mini
```

GGUF Release: Handcrafted APEX-I-MiniPlus (3.36 BPW) for 4GB-24GB VRAM setups

by IsValorum - opened 5 days ago

Discussion

IsValorum

5 days ago

Hugging Face CLI

Hi everyone!

I have created and published a custom, handcrafted APEX-I-MiniPlus (3.36 BPW) quantization of Iris-mini:
👉 IsValorum/Iris-mini-MTP-APEX-I-MiniPlus-GGUF

Key Highlights & Benchmarks:

Custom Mixed-Precision Architecture: Built using deep multi-domain importance matrix (imatrix). Sensitive core routing and embedding layers are protected in Q4_K/Q5_K while inactive expert weights are compressed to IQ3_XXS/IQ3_S.
Budget Hardware / 4GB VRAM Capable: Empirically verified in Unsloth Studio. Uses only ~3.8 GB VRAM with remaining weights offloaded to RAM (DDR4 3200). With MTP disabled, it delivers 23 to 26+ tok/s generation and 300 to 410 tok/s prefill on budget laptop hardware.
Full Context Scalability: Fully documented for 24GB GPUs supporting the full native context window with Q8 KV cache.

Feel free to check it out!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment