Instructions to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16")
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 RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16

SGLang

How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 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 "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16" \
    --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": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16",
		"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 "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16" \
        --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": "RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen3-30B-A3B-Instruct-2507-quantized.w4a16
```

ChibuUkachi commited on Mar 20

Commit

e9c59cd

verified ·

1 Parent(s): d748961

remove category

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -207,10 +207,10 @@ The model was evaluated on the ifeval, mmlu_pro and gsm8k_platinum  using [lm-ev
 ### Accuracy
-| Category | Benchmark | Qwen3-30B-A3B Instruct | Qwen3-30B-A3B Instruct.w4a16 | Recovery (%) |
-|----------|--------|-------------|-------------------|--------------|
-| lmeval | GSM8k Platinum (5-shot) | 96.11 | 95.78 | 99.66 |
-|  | MMLU-Cot (5-shot) | 84.29 | 83.50 | 99.07 |
-|  | MMLU-Pro (5-shot) | 78.90 | 77.11 | 97.73 |
-|  | IfEval  | 89.13 | 89.13| 100.0 |
-| Reasoning (generation) | Math 500 | 89.91 |  92.20 | 102.54 |

 ### Accuracy
+| Benchmark | Qwen3-30B-A3B Instruct | Qwen3-30B-A3B Instruct.w4a16 (this model) | Recovery (%) |
+|--------|-------------|-------------------|--------------|
+| GSM8k Platinum (5-shot) | 96.11 | 95.78 | 99.66 |
+| MMLU-Cot (5-shot) | 84.29 | 83.50 | 99.07 |
+| MMLU-Pro (5-shot) | 78.90 | 77.11 | 97.73 |
+| IfEval  | 89.13 | 89.13| 100.0 |
+| Math 500 | 89.91 |  92.20 | 102.54 |