Instructions to use Neura-Tech-AI/Neuron-27B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neura-Tech-AI/Neuron-27B-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="Neura-Tech-AI/Neuron-27B-Thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Neura-Tech-AI/Neuron-27B-Thinking")
model = AutoModelForCausalLM.from_pretrained("Neura-Tech-AI/Neuron-27B-Thinking", 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=256)
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-27B-Thinking 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-27B-Thinking"
# 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-27B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Neura-Tech-AI/Neuron-27B-Thinking

SGLang

How to use Neura-Tech-AI/Neuron-27B-Thinking 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-27B-Thinking" \
    --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-27B-Thinking",
		"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-27B-Thinking" \
        --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-27B-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Neura-Tech-AI/Neuron-27B-Thinking with Docker Model Runner:
```
docker model run hf.co/Neura-Tech-AI/Neuron-27B-Thinking
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🧠 Neuron-27B-Thinking: The Official Intelligence of Neura Tech AI

Neuron-27B-Thinking is a high-performance Large Language Model (LLM) developed by Neura Tech AI. It is engineered as a powerful reasoning-focused assistant with strong multilingual capabilities and native thinking support.

🏢 Organization Identity

Company: Neura Tech AI
Project Name: Neuron-27B-Thinking

📊 Model Specifications

Architecture: Causal Language Model (Optimized from Qwen3-27B)
Parameters: ~27 Billion
Precision: BF16 (Bfloat16)
Context Window: 262K tokens
Format: ChatML Compatible with native thinking tags
License: Apache-2.0

🎯 Core Capabilities

Advanced Reasoning: Strong performance on complex logical, mathematical, and multi-step problems.
Native Thinking Mode: Supports structured reasoning with <think> blocks for transparent thought process.
Multilingual Proficiency: Highly optimized for English, Hindi, Chinese, Spanish, French, German, Arabic, Japanese, Korean, Portuguese, Russian, etc.
Instruction Following: Precise adherence to complex user instructions.
Creative Synthesis: Excellent at generating technical content, explanations, and structured outputs.

🛠️ Quick Start (Python)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Neura-Tech-AI/Neuron-27B-Thinking"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Who are you?"}
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    inputs,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.9,
    do_sample=True
)

print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))

📜 License

This model is released under the Apache-2.0 License. You are free to use, modify, and distribute it, provided you credit Neura Tech AI as the original developer. Base model weights are derived from the Qwen3.8 family. Please respect the original Qwen license terms where applicable.