Instructions to use drawais/Qwen3.5-9B-AWQ-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drawais/Qwen3.5-9B-AWQ-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="drawais/Qwen3.5-9B-AWQ-INT4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("drawais/Qwen3.5-9B-AWQ-INT4")
model = AutoModelForCausalLM.from_pretrained("drawais/Qwen3.5-9B-AWQ-INT4")
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 drawais/Qwen3.5-9B-AWQ-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drawais/Qwen3.5-9B-AWQ-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drawais/Qwen3.5-9B-AWQ-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/drawais/Qwen3.5-9B-AWQ-INT4

SGLang

How to use drawais/Qwen3.5-9B-AWQ-INT4 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 "drawais/Qwen3.5-9B-AWQ-INT4" \
    --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": "drawais/Qwen3.5-9B-AWQ-INT4",
		"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 "drawais/Qwen3.5-9B-AWQ-INT4" \
        --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": "drawais/Qwen3.5-9B-AWQ-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use drawais/Qwen3.5-9B-AWQ-INT4 with Docker Model Runner:
```
docker model run hf.co/drawais/Qwen3.5-9B-AWQ-INT4
```

Qwen3.5-9B-AWQ-INT4 / config.json

drawais

Initial upload of Qwen3.5-9B-AWQ-INT4

08fbb15 verified 7 days ago

raw

history blame contribute delete

2.94 kB

	{
	"architectures": [
	"Qwen3_5ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 32,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"mlp_only_layers": [],
	"model_type": "qwen3_5_text",
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 16,
	"num_hidden_layers": 32,
	"num_key_value_heads": 4,
	"pad_token_id": null,
	"partial_rotary_factor": 0.25,
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"format": "pack-quantized",
	"input_activations": null,
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": 128,
	"num_bits": 4,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": null,
	"strategy": "group",
	"symmetric": true,
	"type": "int",
	"zp_dtype": null
	}
	}
	},
	"format": "pack-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"lm_head"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.15.1.a20260428"
	},
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	11,
	11,
	10
	],
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.8.0.dev0",
	"use_cache": true,
	"vocab_size": 248320
	}