Instructions to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf with Transformers:

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

pipe = pipeline("text-generation", model="dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf")
model = AutoModelForCausalLM.from_pretrained("dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf

SGLang

How to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf 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 "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf" \
    --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": "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf",
		"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 "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf" \
        --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": "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf with Docker Model Runner:
```
docker model run hf.co/dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf
```

dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf

This repository contains a Hugging Face export of Qwen3-30B-A3B-Instruct-2507 quantized with AQLM using the 2-bit 2x8 scheme.

Base model

Qwen/Qwen3-30B-A3B-Instruct-2507

Quantization

Method: AQLM
Scheme: 2x8
Effective label: 2-bit
Source checkpoint: /work/bduan1/quantized_models/Qwen3-30B-A3B-AQLM-2bit-2x8

Conversion

This repo was produced with convert_to_hf.py from the AQLM project, then exported with --save_safetensors and --save_tokenizer.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

Downloads last month: 11

Safetensors

Model size

8B params

Tensor type

F16

Model tree for dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf

Base model

Qwen/Qwen3-30B-A3B-Instruct-2507

Quantized

(135)

this model

Collection including dbw6/Qwen3-30B-A3B-Instruct-2507-AQLM-2Bit-2x8-hf

EVA

Collection

8 items • Updated Apr 5 • 2