Instructions to use bombman/Qwen3.6-35B-A3B-4bit-Native with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bombman/Qwen3.6-35B-A3B-4bit-Native with Transformers:

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

pipe = pipeline("text-generation", model="bombman/Qwen3.6-35B-A3B-4bit-Native")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bombman/Qwen3.6-35B-A3B-4bit-Native")
model = AutoModelForCausalLM.from_pretrained("bombman/Qwen3.6-35B-A3B-4bit-Native", 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 bombman/Qwen3.6-35B-A3B-4bit-Native with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bombman/Qwen3.6-35B-A3B-4bit-Native"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bombman/Qwen3.6-35B-A3B-4bit-Native",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bombman/Qwen3.6-35B-A3B-4bit-Native

SGLang

How to use bombman/Qwen3.6-35B-A3B-4bit-Native 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 "bombman/Qwen3.6-35B-A3B-4bit-Native" \
    --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": "bombman/Qwen3.6-35B-A3B-4bit-Native",
		"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 "bombman/Qwen3.6-35B-A3B-4bit-Native" \
        --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": "bombman/Qwen3.6-35B-A3B-4bit-Native",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bombman/Qwen3.6-35B-A3B-4bit-Native with Docker Model Runner:
```
docker model run hf.co/bombman/Qwen3.6-35B-A3B-4bit-Native
```

Qwen3.6-35B-A3B-4bit-Native This repository provides the 4-bit (NF4) quantized weights for the Qwen3.6-35B-A3B Mixture-of-Experts model. These weights were generated using the bitsandbytes library with double quantization enabled to ensure maximum precision at a reduced memory footprint.

Model Details

Base Model: Qwen3.6-35B-A3B Quantization: 4-bit NormalFloat (NF4) Framework: Hugging Face Transformers Total Parameters: ~35B Expert Architecture: 256 Experts per Layer

Key Features

Native Compatibility: Designed to work seamlessly with the transformers library without additional conversion layers. Memory Efficiency: Optimized to fit within ~20GB of memory (VRAM/RAM combined), making it accessible for mid-range hardware environments. Precision: Uses Double Quantization to minimize perplexity degradation compared to the original BF16 weights.

Downloads last month: 27

Safetensors

Model size

35B params

Tensor type

F32

BF16

Model tree for bombman/Qwen3.6-35B-A3B-4bit-Native

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(757)

this model