Instructions to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact with Transformers:

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

pipe = pipeline("text-generation", model="QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", trust_remote_code=True)
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 QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact"
# 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-R1-0528-GPTQ-Int4-Int8Mix-Compact",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact

SGLang

How to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact 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-R1-0528-GPTQ-Int4-Int8Mix-Compact" \
    --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-R1-0528-GPTQ-Int4-Int8Mix-Compact",
		"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-R1-0528-GPTQ-Int4-Int8Mix-Compact" \
        --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-R1-0528-GPTQ-Int4-Int8Mix-Compact",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact with Docker Model Runner:
```
docker model run hf.co/QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact
```

tclf90 commited on Jun 1, 2025

Commit

aa85e6a

verified ·

1 Parent(s): 6ddb807

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -3

README.md CHANGED Viewed

@@ -15,11 +15,23 @@ base_model_relation: quantized
 # DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact
 Base mode [deepseek-ai/DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528)
-This repository contains a mixed-precision (Int4 + selective Int8) GPTQ version of DeepSeek-R1-0528 for vLLM. We began with a standard 4-bit (AWQ/GPTQ) conversion that follows vLLM’s default quantization layout, but early tests showed that a fully-Int4 model could not meet the compute demands of this checkpoint and may produce unstable outputs.
-Guided by this preliminary analysis, we introduced targeted, per-layer Int8 refinement: only the layers most sensitive to quantization are stored in lnt8 (the compadct version has more int8 layers), while the rest remain Int4. This keeps the file-size increase minimal compared with the pure 4-bit baseline while restoring response quality.
-Currently, vllm==0.9.0 does not support per-layer quantization settings for the moe module. I've provided a basic implementation by adding the get_moe_quant_method function within the gptq_marlin.py file. Before the PR is merged, please replace the corresponding file with the attached one.
 ### 【Model Update Date】
 ```

 # DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact
 Base mode [deepseek-ai/DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528)
+This repository delivers an Int4 + selectively-Int8 GPTQ `DeepSeek-R1-0528` model: only layers that are highly sensitive to quantization remain in Int8, while the rest stay Int4—preserving generation quality with minimal file-size overhead.
+Preliminary trials show that converting the entire model to pure Int4 (AWQ/GPTQ) under the quantization layout used in vLLM’s current DeepSeek-R1 implementation degrades inference accuracy and can produce faulty outputs. Layer-wise fine-grained quantization substantially mitigates this issue.
+    Temporary patch:
+    vLLM == 0.9.0 does not yet natively support per-layer quantization for MoE modules.
+    We added get_moe_quant_method to gptq_marlin.py as an interim fix.
+    Until the upstream PR is merged, please replace the original file with the one provided in this repo.
+Variant Overview
+| Variant     | Characteristics                                                         | File Size | Recommended Scenario                                     |
+|-------------|-------------------------------------------------------------------------|-----------|----------------------------------------------------------|
+| **Compact** | More Int8 layers, higher fidelity                                       | 414 GB    | Ample GPU memory & strict quality needs (e.g., 8 × A100) |
+| **Lite**    | Only the most critical layers upgraded to Int8; size close to pure Int4 | 355 GB    | Resource-constrained, lightweight server deployments     |
+Choose the variant that best matches your hardware and quality requirements.
 ### 【Model Update Date】
 ```