Instructions to use HyzeAI/HyzeQwenInstruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HyzeAI/HyzeQwenInstruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="HyzeAI/HyzeQwenInstruct")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("HyzeAI/HyzeQwenInstruct")
model = AutoModelForMultimodalLM.from_pretrained("HyzeAI/HyzeQwenInstruct", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HyzeAI/HyzeQwenInstruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HyzeAI/HyzeQwenInstruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HyzeAI/HyzeQwenInstruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/HyzeAI/HyzeQwenInstruct

SGLang

How to use HyzeAI/HyzeQwenInstruct 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 "HyzeAI/HyzeQwenInstruct" \
    --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": "HyzeAI/HyzeQwenInstruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "HyzeAI/HyzeQwenInstruct" \
        --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": "HyzeAI/HyzeQwenInstruct",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use HyzeAI/HyzeQwenInstruct with Docker Model Runner:
```
docker model run hf.co/HyzeAI/HyzeQwenInstruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Hyze Logo

Qwen Logo

HyzeQwenInstruct-30B

A high-performance instruction model by Hyze AI built for coding and research.

🔗 Chat with all models • 📘 HyzeAcademy • 🧠 HyzeNote (NotebookLM alternate)

🚀 Overview

HyzeQwenInstruct-30B is a 30-billion parameter instruction-tuned large language model optimized for:

🧑‍💻 Advanced code generation
📚 Technical research & reasoning
🧠 Deep structured explanations
🤖 Strong instruction following

Designed for developers, engineers, and researchers who need powerful AI assistance.

🧠 Training Focus

HyzeQwenInstruct-30B was optimized for:

🧑‍💻 Coding

Python, JavaScript, C++, and more
Code completion & generation
Debugging & refactoring
Algorithm explanations

📊 Research & Technical Reasoning

Structured academic-style answers
Scientific explanations
Step-by-step reasoning
Long-form responses

🎯 Instruction Tuning

Precise intent following
Context retention
Clean output formatting

📊 Benchmarks — Technical Comparison

Model	Size	Coding	Reasoning	Notes
HyzeQwenInstruct-30B	30B	⭐⭐⭐⭐☆	⭐⭐⭐⭐☆	Optimized for dev + research
Qwen-30B-Instruct	30B	⭐⭐⭐⭐☆	⭐⭐⭐⭐☆	Strong base alignment
GPT-NeoX-20B	20B	⭐⭐⭐☆☆	⭐⭐⭐☆☆	Smaller parameter count
GPT-1	117M	⭐⭐☆☆☆	⭐⭐☆☆☆	Early generation model

⚡ Performance Characteristics

Strong code structure generation
Clear technical explanations
High instruction accuracy
Suitable for professional workflows

Benchmark ratings are based on internal qualitative evaluation.

🧪 Usage

Transformers (Python)

from transformers import pipeline

generator = pipeline(
    "text-generation",
    model="HyzeAI/HyzeQwenInstruct-30B"
)

print(generator("Write a Python function to implement quicksort:"))

Downloads last month: 15

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for HyzeAI/HyzeQwenInstruct

Base model

Qwen/Qwen3-VL-30B-A3B-Instruct

Finetuned

(41)

this model

Quantizations

12 models