Instructions to use Neura-Tech-AI/Neuron-6x4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neura-Tech-AI/Neuron-6x4B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Neura-Tech-AI/Neuron-6x4B-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-6x4B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Neura-Tech-AI/Neuron-6x4B-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-6x4B-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-6x4B-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-6x4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Neura-Tech-AI/Neuron-6x4B-Instruct

SGLang

How to use Neura-Tech-AI/Neuron-6x4B-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-6x4B-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-6x4B-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-6x4B-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-6x4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Neura-Tech-AI/Neuron-6x4B-Instruct with Docker Model Runner:
```
docker model run hf.co/Neura-Tech-AI/Neuron-6x4B-Instruct
```

Neura-Tech-AI commited on 3 days ago

Commit

94a4e8e

verified ·

1 Parent(s): 252b978

Create NOTICE

Browse files

Files changed (1) hide show

NOTICE +92 -0

NOTICE ADDED Viewed

	@@ -0,0 +1,92 @@

+Neuron-6x4B-Instruct
+Copyright (c) 2026 Neura Tech AI
+Neuron-6x4B-Instruct is an open-source Mixture of Experts (MoE) large language
+model developed by Neura Tech AI.
+This model is built upon the following base models:
+- Neura-Tech-AI/Neuron-4B-Instruct
+  Copyright (c) 2026 Neura Tech AI.
+- Qwen/Qwen3-4B-Instruct-2507
+  Copyright (c) 2024 Alibaba Cloud and the Qwen Team.
+- Qwen/Qwen3-4B-Thinking-2507
+  Copyright (c) 2024 Alibaba Cloud and the Qwen Team.
+Neuron-4B-Instruct is based on the Qwen3 architecture and includes additional
+modifications and improvements developed by Neura Tech AI.
+The original Qwen3 models are licensed under the Apache License,
+Version 2.0. A copy of the Apache License is included in the LICENSE file.
+Neuron-6x4B-Instruct introduces additional modifications made by
+Neura Tech AI, including but not limited to:
+- Mixture of Experts (MoE) architecture
+- Six-expert sparse routing design
+- Dynamic expert routing configuration
+- Expert composition and parameter merging
+- Instruction tuning improvements
+- Identity customization
+- Chat template customization
+- Alignment improvements
+- Reasoning enhancements
+- Multilingual capability improvements
+- Coding and software engineering optimization
+- Tool-calling optimization
+- Long-context support optimization
+- Dataset improvements
+- Branding and documentation
+- Model packaging and distribution
+These modifications are Copyright (c) 2026
+Neura Tech AI.
+Developer
+Neura Tech AI
+Official AI Research & Development Organization
+Project
+Neuron
+Model
+Neuron-6x4B-Instruct
+Architecture
+Sparse Transformer Decoder
+Mixture of Experts (MoE)
+Qwen3 Architecture
+Base Models
+- Neura-Tech-AI/Neuron-4B-Instruct
+- Qwen/Qwen3-4B-Instruct-2507
+- Qwen/Qwen3-4B-Thinking-2507
+Model Highlights
+- Approximately 24 Billion Total Parameters
+- Six Specialized Experts
+- Dynamic Sparse Expert Routing
+- Instruction-Tuned
+- Multilingual Language Model
+- Optimized for Reasoning, Coding, Mathematics, Tool Calling,
+  Agentic Workflows, and Long-Context Understanding
+Acknowledgment
+We sincerely thank Alibaba Cloud and the Qwen Team for releasing the
+Qwen3 model family under the Apache License, Version 2.0. Their work
+served as the architectural foundation that enabled the development of
+Neuron-4B-Instruct and, subsequently, Neuron-6x4B-Instruct.
+This NOTICE file is provided solely for attribution purposes and does
+not modify, replace, or supersede the terms of the Apache License,
+Version 2.0.