Instructions to use DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT with Transformers:

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

pipe = pipeline("text-generation", model="DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT")
model = AutoModelForCausalLM.from_pretrained("DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-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

vLLM

How to use DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-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": "DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT

SGLang

How to use DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-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 "DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-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": "DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-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 "DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-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": "DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT",
    max_seq_length=2048,
)

Docker Model Runner
How to use DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT with Docker Model Runner:
```
docker model run hf.co/DavidAU/Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3-30B-A3B-YOYO-V2-Claude-4.6-Opus-High-INSTRUCT

The power of Claude 4.5 Opus High Reasoning with the MOE power (and speed) of Qwen 30B-A3B 2507 Thinking (256k context, 128 experts) combined with YOYO2 Merge creating an INSTRUCT hybrid of unmatched power.

Benchmarks (below) show that this version exceeds the org model in 8 out of 8 metrics - some by a lightyear.

It is not even close to "org" model specs.

Tuning via Unsloth (on local hardware) using Linux for Windows I created a specialized tuned Claude Opus 4.6 High Reasoning adapter.

Compact, to the point, and powerful reasoning takes "Qwen 30B-A3B YOYO V2" to the next level. Small reasoning traces may appear as text during some generations - but this is an instruct model.

Note all math, science and other goodies are fully intact.

Model Specs:

256k context
128 experts (8 active by default)
3B of 30B parameters active.
Model can be used on GPU, CPU or split at reasonable token/second speed.

BENCHMARKS:

[ xxx ] - Exceeds org model specs.

ARC-Challenge | ARC-Easy | BoolQ   | Hellaswag | OpenBookQA | PIQA  | Winogrande
[0.545]         [0.717]    [0.877]   [0.717]     [0.440]     [0.789]  [0.653]

VS "Normal Qwen3 30B-A3B"

ARC-Challenge | ARC-Easy | BoolQ | Hellaswag | OpenBookQA | PIQA  | Winogrande
0.410           0.444      0.691   0.635       0.390        0.769   0.650

Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:

In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;

Set the "Smoothing_factor" to 1.5

: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"

: in text-generation-webui -> parameters -> lower right.

: In Silly Tavern this is called: "Smoothing"

NOTE: For "text-generation-webui"

-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)

Source versions (and config files) of my models are here:

https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be

OTHER OPTIONS:

Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.

Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers

This a "Class 1" model:

For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]

You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:

[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]