Instructions to use Vortex5/G4-Midnight-Macaw-26B-A4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vortex5/G4-Midnight-Macaw-26B-A4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Vortex5/G4-Midnight-Macaw-26B-A4B")
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("Vortex5/G4-Midnight-Macaw-26B-A4B")
model = AutoModelForMultimodalLM.from_pretrained("Vortex5/G4-Midnight-Macaw-26B-A4B", 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 Vortex5/G4-Midnight-Macaw-26B-A4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vortex5/G4-Midnight-Macaw-26B-A4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/G4-Midnight-Macaw-26B-A4B",
		"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/Vortex5/G4-Midnight-Macaw-26B-A4B

SGLang

How to use Vortex5/G4-Midnight-Macaw-26B-A4B 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 "Vortex5/G4-Midnight-Macaw-26B-A4B" \
    --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": "Vortex5/G4-Midnight-Macaw-26B-A4B",
		"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 "Vortex5/G4-Midnight-Macaw-26B-A4B" \
        --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": "Vortex5/G4-Midnight-Macaw-26B-A4B",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Vortex5/G4-Midnight-Macaw-26B-A4B with Docker Model Runner:
```
docker model run hf.co/Vortex5/G4-Midnight-Macaw-26B-A4B
```

This is the fastest Gemma 4 26b a4b model I've ever used.

by DorkMckork1 - opened 2 days ago

Discussion

DorkMckork1

2 days ago

It gets up to 58 tokens per second on my hardware with full context, GPU offload at max, CPU threads set to 8 (on AMD AM4 platform, Ryzen 5700x3d, Radeon RX 7700, Radeon RX 7600, 64 gigabytes of ram) It runs super fast and so far it stays solid in intelligence and reasoning at IQ4_XS quants. Excellent model! I'm getting this speed under Vulkan Llama.cpp. Awesome release. I'm using the mradermacher weighted quants (IQ4_XS) It runs great agentically, I'm using it in Odysseus and it does tool calls great. Thanks for this release, its really smart and really fast.

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