Instructions to use Nexa-AI-Official/Nexa-AI-4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nexa-AI-Official/Nexa-AI-4B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Nexa-AI-Official/Nexa-AI-4B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nexa-AI-Official/Nexa-AI-4B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Nexa-AI-Official/Nexa-AI-4B-Instruct")
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 Nexa-AI-Official/Nexa-AI-4B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nexa-AI-Official/Nexa-AI-4B-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": "Nexa-AI-Official/Nexa-AI-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nexa-AI-Official/Nexa-AI-4B-Instruct

SGLang

How to use Nexa-AI-Official/Nexa-AI-4B-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 "Nexa-AI-Official/Nexa-AI-4B-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": "Nexa-AI-Official/Nexa-AI-4B-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 "Nexa-AI-Official/Nexa-AI-4B-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": "Nexa-AI-Official/Nexa-AI-4B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nexa-AI-Official/Nexa-AI-4B-Instruct with Docker Model Runner:
```
docker model run hf.co/Nexa-AI-Official/Nexa-AI-4B-Instruct
```

Nexa-AI-4B-Instruct / README.md

Neura-Tech-AI

Update README.md

17fbe35 verified 1 day ago

preview code

Raw

History Blame Contribute Delete

3.35 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: Qwen/Qwen3-4B-Instruct-2507
	pipeline_tag: text-generation
	language:
	- en
	- hi
	- zh
	new_version: Neura-Tech-AI/Nexa-AI-4B-Instruct
	tags:
	- Neura Tech AI
	- Lumina AI
	- Nexa AI
	- instruct
	- llm
	- transformer
	- qwen
	- multilingual
	- conversational
	---

	# Nexa-AI-4B-Instruct

	> A collaborative open-source large language model developed by Neura Tech AI and Lumina AI.

	## Overview

	Nexa-AI-4B-Instruct is an instruction-tuned large language model built on top of Qwen/Qwen3-4B-Instruct-2507.

	This project is jointly developed by:

	- Neura Tech AI
	- Lumina AI

	Nexa AI focuses on delivering a capable multilingual AI assistant with strong performance in:

	- General conversation
	- Instruction following
	- Coding
	- Mathematics
	- Logical reasoning
	- Tool calling & AI agents
	- Multilingual understanding (including English, Hindi, Chinese, and more)

	## Base Model

	Base Model: `Qwen/Qwen3-4B-Instruct-2507`

	We sincerely thank the Qwen Team for releasing the Qwen3 model family under the Apache 2.0 License, which made this project possible.

	## Developers

	Project: Nexa AI

	Developed by:
	- Neura Tech AI
	- Lumina AI

	## Model Details

	- Model Name: Nexa-AI-4B-Instruct
	- Base Model: Qwen/Qwen3-4B-Instruct-2507
	- Architecture: Transformer Decoder
	- Parameters: ~4 Billion
	- Context Length: 262,144 Tokens (Inherited from the base model)
	- License: Apache-2.0 (Base model license)

	## Features

	- High-quality instruction following
	- Coding assistance
	- Mathematical reasoning
	- Agent & tool calling support
	- Multilingual capabilities
	- Long-context understanding
	- Fine-tuned alignment for helpful responses
	-

	## Performance

	\| \| GPT-4.1-nano-2025-04-14 \| Qwen3-30B-A3B Non-Thinking \| Qwen3-4B Non-Thinking \| Nexa-AI-4B-Instruct \|
	\|--- \| --- \| --- \| --- \| --- \|
	\| Knowledge \| \| \| \|
	\| MMLU-Pro \| 62.8 \| 69.1 \| 58.0 \| 69.6 \|
	\| MMLU-Redux \| 80.2 \| 84.1 \| 77.3 \| 84.2 \|
	\| GPQA \| 50.3 \| 54.8 \| 41.7 \| 62.0 \|
	\| SuperGPQA \| 32.2 \| 42.2 \| 32.0 \| 42.8 \|
	\| Reasoning \| \| \| \|
	\| AIME25 \| 22.7 \| 21.6 \| 19.1 \| 47.4 \|
	\| HMMT25 \| 9.7 \| 12.0 \| 12.1 \| 31.0 \|
	\| ZebraLogic \| 14.8 \| 33.2 \| 35.2 \| 80.2 \|
	\| LiveBench 20241125 \| 41.5 \| 59.4 \| 48.4 \| 63.0 \|
	\| Coding \| \| \| \|
	\| LiveCodeBench v6 (25.02-25.05) \| 31.5 \| 29.0 \| 26.4 \| 35.1 \|
	\| MultiPL-E \| 76.3 \| 74.6 \| 66.6 \| 76.8 \|
	\| Aider-Polyglot \| 9.8 \| 24.4 \| 13.8 \| 12.9 \|
	\| Alignment \| \| \| \|
	\| IFEval \| 74.5 \| 83.7 \| 81.2 \| 83.4 \|
	\| Arena-Hard v2* \| 15.9 \| 24.8 \| 9.5 \| 43.4 \|
	\| Creative Writing v3 \| 72.7 \| 68.1 \| 53.6 \| 83.5 \|
	\| WritingBench \| 66.9 \| 72.2 \| 68.5 \| 83.4 \|
	\| Agent \| \| \| \|
	\| BFCL-v3 \| 53.0 \| 58.6 \| 57.6 \| 61.9 \|
	\| TAU1-Retail \| 23.5 \| 38.3 \| 24.3 \| 48.7 \|
	\| TAU1-Airline \| 14.0 \| 18.0 \| 16.0 \| 32.0 \|
	\| TAU2-Retail \| - \| 31.6 \| 28.1 \| 40.4 \|
	\| TAU2-Airline \| - \| 18.0 \| 12.0 \| 24.0 \|
	\| TAU2-Telecom \| - \| 18.4 \| 17.5 \| 13.2 \|
	\| Multilingualism \| \| \| \|
	\| MultiIF \| 60.7 \| 70.8 \| 61.3 \| 69.0 \|
	\| MMLU-ProX \| 56.2 \| 65.1 \| 49.6 \| 61.6 \|
	\| INCLUDE \| 58.6 \| 67.8 \| 53.8 \| 60.1 \|
	\| PolyMATH \| 15.6 \| 23.3 \| 16.6 \| 31.1 \|

	*: For reproducibility, we report the win rates evaluated by GPT-4.1.

	## © 2026 Neura Tech AI & Lumina AI. All rights reserved.