Instructions to use QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite with Transformers:

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

pipe = pipeline("text-generation", model="QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite

SGLang

How to use QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite 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 "QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite" \
    --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": "QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite",
		"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 "QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite" \
        --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": "QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite with Docker Model Runner:
```
docker model run hf.co/QuantTrio/DeepSeek-V3.2-Exp-AWQ-Lite
```

What does “Lite” mean?

by jairo - opened Oct 6, 2025

Discussion

jairo

Oct 6, 2025

other than the size difference (from 373 GB to 339 GB) what else is different? What does “Lite” mean here? thanks!

tclf90

QuantTrio org Oct 7, 2025

•

edited Oct 7, 2025

Size difference only — more layers have been quantized to 4-bit.

Here’s the catch:

DeepSeek V3 series generally perform poorly under int-4 bit quantization (can’t maintain stable outputs).
To make AWQ quants still work, we usually keep some critical layers unquantized so that the model can output properly.
Those variants are still named with the suffix -AWQ (yeah, the naming is a bit loose here) and typically take up around 373 GB.
Some of the DeepSeek V3 NVFP4 repos on HF actually keep even more layers unquantized (over 400 GB total size),
yet this is not reflected in their naming — which makes things a bit confusing overall.

However, some of these V3 variants surprisingly work fine under the regular AWQ strategy (all the desired layers are quantized ).
So we released these as AWQ-Lite — same architecture, but with more layers fully quantized to 4-bit, resulting in a smaller size (≈ 339 GB).

That said, the DeepSeek V3 series still have unresolved issues with quantization quality, and haven’t seen much improvement so far.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment