Instructions to use XReyRobert/Nex-N2-mini-GPTQ-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XReyRobert/Nex-N2-mini-GPTQ-Pro with Transformers:

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

pipe = pipeline("text-generation", model="XReyRobert/Nex-N2-mini-GPTQ-Pro")
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("XReyRobert/Nex-N2-mini-GPTQ-Pro")
model = AutoModelForMultimodalLM.from_pretrained("XReyRobert/Nex-N2-mini-GPTQ-Pro", 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 XReyRobert/Nex-N2-mini-GPTQ-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XReyRobert/Nex-N2-mini-GPTQ-Pro"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XReyRobert/Nex-N2-mini-GPTQ-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XReyRobert/Nex-N2-mini-GPTQ-Pro

SGLang

How to use XReyRobert/Nex-N2-mini-GPTQ-Pro 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 "XReyRobert/Nex-N2-mini-GPTQ-Pro" \
    --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": "XReyRobert/Nex-N2-mini-GPTQ-Pro",
		"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 "XReyRobert/Nex-N2-mini-GPTQ-Pro" \
        --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": "XReyRobert/Nex-N2-mini-GPTQ-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XReyRobert/Nex-N2-mini-GPTQ-Pro with Docker Model Runner:
```
docker model run hf.co/XReyRobert/Nex-N2-mini-GPTQ-Pro
```

Nex-N2-mini-GPTQ-Pro / UPLOAD_MANIFEST.json

XReyRobert

Update Nex-N2-mini GPTQ-Pro non-VL metadata

77a0b9f verified 3 months ago

Raw

History Blame Contribute Delete

3.61 kB

	{
	"created_at": "2026-06-16T19:21:52.349847+00:00",
	"files": [
	{
	"path": "README.md",
	"size": 2567
	},
	{
	"path": "UPLOAD_MANIFEST.json",
	"size": 3606
	},
	{
	"path": "chat_template.jinja",
	"size": 7747
	},
	{
	"path": "config.json",
	"size": 5598
	},
	{
	"path": "generation_config.json",
	"size": 162
	},
	{
	"path": "model-00001-of-00005.safetensors",
	"size": 4296105224
	},
	{
	"path": "model-00002-of-00005.safetensors",
	"size": 4298580456
	},
	{
	"path": "model-00003-of-00005.safetensors",
	"size": 4298546944
	},
	{
	"path": "model-00004-of-00005.safetensors",
	"size": 4298596456
	},
	{
	"path": "model-00005-of-00005.safetensors",
	"size": 3460854912
	},
	{
	"path": "model.safetensors.index.json",
	"size": 13150295
	},
	{
	"path": "processor_config.json",
	"size": 1297
	},
	{
	"path": "quantize_config.json",
	"size": 1847
	},
	{
	"path": "tokenizer.json",
	"size": 19989343
	},
	{
	"path": "tokenizer_config.json",
	"size": 1219
	}
	],
	"inspection": {
	"architectures": [
	"Qwen3_5MoeForConditionalGeneration"
	],
	"artifact": "/workspace/out/nex-n2-mini/GPTQ-Pro-FOEM-4bit-g128-ns256-text-main",
	"config_model_type": "qwen3_5_moe",
	"has_mtp_tensors": false,
	"has_vision_tensors": true,
	"index_keys": 124576,
	"metadata_total_size": 20652683992,
	"metadata_total_size_matches": true,
	"quant_meta": {
	"act_group_aware": true,
	"activation_weighted_mse": true,
	"auto_forward_data_parallel": true,
	"calibration_dataset": "wikitext",
	"damp_auto_increment": 0.01,
	"damp_percent": 0.05,
	"dense_vram_strategy": "exclusive",
	"dense_vram_strategy_devices": [
	"cuda:0"
	],
	"fallback": {
	"smooth": {
	"group_size_threshold": 128,
	"maxshrink": 0.9,
	"steps": 32,
	"type": "mse"
	},
	"strategy": "rtn",
	"threshold": "0.5%"
	},
	"foem": {
	"alpha": 0.25,
	"beta": 0.2,
	"device": "cuda:0"
	},
	"gc_mode": "interval",
	"gptaq": null,
	"hessian": {
	"chunk_bytes": null,
	"chunk_size": null,
	"staging_dtype": "float32"
	},
	"mock_quantization": false,
	"moe": {
	"routing": {
	"batch_size": 320,
	"class": "ExpertsRoutingBypass"
	}
	},
	"moe_vram_strategy": "balanced",
	"moe_vram_strategy_devices": [
	"cuda:0"
	],
	"mse": 2.0,
	"nsamples": 256,
	"offload_to_disk": false,
	"offload_to_disk_path": null,
	"pack_impl": "cpu",
	"quantizer": [
	"gptqmodel:6.1.0-dev"
	],
	"reference_recipe": "groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit",
	"seqlen": 2048,
	"source_model": "nex-agi/Nex-N2-mini",
	"static_groups": false,
	"true_sequential": true,
	"uri": "https://github.com/modelcloud/gptqmodel",
	"wait_for_submodule_finalizers": false
	},
	"qweight_tensors": 30970,
	"referenced_shards": [
	"model-00001-of-00005.safetensors",
	"model-00002-of-00005.safetensors",
	"model-00003-of-00005.safetensors",
	"model-00004-of-00005.safetensors",
	"model-00005-of-00005.safetensors"
	],
	"safetensors_bytes": 20652683992,
	"safetensors_count": 5,
	"unreferenced_shards": []
	},
	"repo_id": "XReyRobert/Nex-N2-mini-GPTQ-Pro"
	}