Instructions to use nex-agi/Nex-N2.5-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nex-agi/Nex-N2.5-mini with Transformers:

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

pipe = pipeline("text-generation", model="nex-agi/Nex-N2.5-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("nex-agi/Nex-N2.5-mini")
model = AutoModelForMultimodalLM.from_pretrained("nex-agi/Nex-N2.5-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 nex-agi/Nex-N2.5-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nex-agi/Nex-N2.5-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": "nex-agi/Nex-N2.5-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nex-agi/Nex-N2.5-mini

SGLang

How to use nex-agi/Nex-N2.5-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 "nex-agi/Nex-N2.5-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": "nex-agi/Nex-N2.5-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 "nex-agi/Nex-N2.5-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": "nex-agi/Nex-N2.5-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nex-agi/Nex-N2.5-mini with Docker Model Runner:
```
docker model run hf.co/nex-agi/Nex-N2.5-mini
```

GGUF Release: Handcrafted APEX-I-MiniPlus (3.36 BPW) + Q8_0 Vision Projector

by IsValorum - opened 5 days ago

Discussion

IsValorum

5 days ago

Hugging Face CLI

Hi community!

I have published a custom, handcrafted APEX-I-MiniPlus (3.36 BPW) quantization of Nex-N2.5-mini, bundled with a dedicated Q8_0 vision projector (mmproj):
👉 IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-GGUF

Highlights:

Preserved Vision Quality: Includes the dedicated mmproj-nex-agi_Nex-N2.5-mini-Q8_0.gguf ensuring near-lossless visual encoding for OCR, document parsing, and agentic screen workflows.
Handcrafted Hybrid Precision: Uses multi-stage imatrix calibration. Preserves critical reasoning pathways and routing weights while optimizing MoE experts down to ~14.5 GB total footprint.
Extreme Hardware Accessibility: Tested and verified on Unsloth Studio. Operates on 4GB VRAM laptops (~3.8 GB VRAM footprint + RAM on DDR4 3200) reaching 23-26+ tok/s generation and 300-410 tok/s prefill without MTP.
Enterprise / 24GB Ready: Full 256k context breakdown provided in the model card for high-end setups.

Check it out and test it with your multimodal workflows!

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