Instructions to use Neura-Tech-AI/Neuron-46x4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neura-Tech-AI/Neuron-46x4B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Neura-Tech-AI/Neuron-46x4B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Neura-Tech-AI/Neuron-46x4B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Neura-Tech-AI/Neuron-46x4B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Neura-Tech-AI/Neuron-46x4B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neura-Tech-AI/Neuron-46x4B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neura-Tech-AI/Neuron-46x4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Neura-Tech-AI/Neuron-46x4B-Instruct

SGLang

How to use Neura-Tech-AI/Neuron-46x4B-Instruct 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 "Neura-Tech-AI/Neuron-46x4B-Instruct" \
    --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": "Neura-Tech-AI/Neuron-46x4B-Instruct",
		"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 "Neura-Tech-AI/Neuron-46x4B-Instruct" \
        --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": "Neura-Tech-AI/Neuron-46x4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Neura-Tech-AI/Neuron-46x4B-Instruct with Docker Model Runner:
```
docker model run hf.co/Neura-Tech-AI/Neuron-46x4B-Instruct
```

Neat

by Harpere - opened about 14 hours ago

Discussion

Harpere

about 14 hours ago

This is something I should know about. May we have more information?

Neura-Tech-AI

Owner about 3 hours ago

•

edited about 3 hours ago

Thanks for your interest!

Neuron-46x4B-Instruct is currently an experimental Mixture-of-Experts (MoE) language model developed by Neura Tech AI. It was created to explore efficient MoE architectures and instruction-following capabilities.

Current details:

Architecture: 125B total parameters (46 experts)
Model type: Instruction-tuned MoE
Base: Qwen3 MoE family
Status: Experimental
Intended use: Research, testing, and community feedback

This is an early release, so more benchmarks, documentation, and future updates will be published as development progresses. Feedback is always welcome!

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