| --- |
| language: |
| - en |
| base_model: |
| - deepseek-ai/DeepSeek-R1-0528 |
| pipeline_tag: text-generation |
| tags: |
| - deepseek_v3 |
| - deepseek |
| - neuralmagic |
| - redhat |
| - llmcompressor |
| - quantized |
| - INT4 |
| - GPTQ |
| - conversational |
| - compressed-tensors |
| license: mit |
| license_name: mit |
| name: RedHatAI/DeepSeek-R1-0528-quantized.w4a16 |
| description: This model was obtained by quantizing weights of DeepSeek-R1-0528 to INT4 data type. |
| readme: https://huggingface.co/RedHatAI/DeepSeek-R1-0528-quantized.w4a16/main/README.md |
| tasks: |
| - text-to-text |
| provider: DeepSeek |
| license_link: https://choosealicense.com/licenses/mit/ |
| validated_on: |
| - RHOAI 2.24 |
| - RHAIIS 3.2.1 |
| - vLLM v0.10.0 |
| --- |
| |
| <h1 style="display: flex; align-items: center; gap: 10px; margin: 0;"> |
| DeepSeek-R1-0528-quantized.w4a16 |
| <img src="https://www.redhat.com/rhdc/managed-files/Catalog-Validated_model_0.png" alt="Model Icon" width="40" style="margin: 0; padding: 0;" /> |
| </h1> |
| |
| <a href="https://www.redhat.com/en/products/ai/validated-models" target="_blank" style="margin: 0; padding: 0;"> |
| <img src="https://www.redhat.com/rhdc/managed-files/Validated_badge-Dark.png" alt="Validated Badge" width="250" style="margin: 0; padding: 0;" /> |
| </a> |
|
|
| ## Model Overview |
| - **Model Architecture:** DeepseekV3ForCausalLM |
| - **Input:** Text |
| - **Output:** Text |
| - **Model Optimizations:** |
| - **Activation quantization:** None |
| - **Weight quantization:** INT4 |
| - **Release Date:** 05/30/2025 |
| - **Version:** 1.0 |
| - **Validated on:** RHOAI 2.24, RHAIIS 3.2.1 |
| - **Model Developers:** Red Hat (Neural Magic) |
| - **ModelCar Storage URI:** oci://registry.redhat.io/rhelai1/modelcar-deepseek-r1-0528-quantized-w4a16:1.5 |
| - **Validated on RHOAI 2.24:** quay.io/modh/vllm:rhoai-2.24-cuda |
| - **Validated on RHAIIS 3.2.1:** http://registry.redhat.io/rhaiis/vllm-cuda-rhel9:3.2.1 |
| - **Validated on vLLM:** 0.10.0 |
|
|
| ### Model Optimizations |
|
|
| This model was obtained by quantizing weights of [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) to INT4 data type. |
| This optimization reduces the number of bits used to represent weights from 8 to 4, reducing GPU memory requirements (by approximately 50%). |
| Weight quantization also reduces disk size requirements by approximately 50%. |
|
|
|
|
| ## Deployment |
|
|
| This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. |
|
|
| ```python |
| from vllm import LLM, SamplingParams |
| from transformers import AutoTokenizer |
| model_id = "RedHatAI/DeepSeek-R1-0528-quantized.w4a16" |
| number_gpus = 8 |
| sampling_params = SamplingParams(temperature=0.6, top_p=0.95, max_tokens=256) |
| tokenizer = AutoTokenizer.from_pretrained(model_id) |
| prompt = "Give me a short introduction to large language model." |
| llm = LLM(model=model_id, tensor_parallel_size=number_gpus) |
| outputs = llm.generate(prompt, sampling_params) |
| generated_text = outputs[0].outputs[0].text |
| print(generated_text) |
| ``` |
|
|
| vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. |
|
|
| <details> |
| <summary>Deploy on <strong>Red Hat AI Inference Server</strong></summary> |
| |
| ```bash |
| podman run --rm -it --device nvidia.com/gpu=all -p 8000:8000 \ |
| --ipc=host \ |
| --env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \ |
| --env "HF_HUB_OFFLINE=0" -v ~/.cache/vllm:/home/vllm/.cache \ |
| --name=vllm \ |
| registry.access.redhat.com/rhaiis/rh-vllm-cuda \ |
| vllm serve \ |
| --tensor-parallel-size 8 \ |
| --max-model-len 32768 \ |
| --enforce-eager --model RedHatAI/DeepSeek-R1-0528-quantized.w4a16 |
| ``` |
| </details> |
|
|
|
|
| <details> |
| <summary>Deploy on <strong>Red Hat Openshift AI</strong></summary> |
| |
| ```python |
| # Setting up vllm server with ServingRuntime |
| # Save as: vllm-servingruntime.yaml |
| apiVersion: serving.kserve.io/v1alpha1 |
| kind: ServingRuntime |
| metadata: |
| name: vllm-cuda-runtime # OPTIONAL CHANGE: set a unique name |
| annotations: |
| openshift.io/display-name: vLLM NVIDIA GPU ServingRuntime for KServe |
| opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]' |
| labels: |
| opendatahub.io/dashboard: 'true' |
| spec: |
| annotations: |
| prometheus.io/port: '8080' |
| prometheus.io/path: '/metrics' |
| multiModel: false |
| supportedModelFormats: |
| - autoSelect: true |
| name: vLLM |
| containers: |
| - name: kserve-container |
| image: quay.io/modh/vllm:rhoai-2.24-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.24-rocm |
| command: |
| - python |
| - -m |
| - vllm.entrypoints.openai.api_server |
| args: |
| - "--port=8080" |
| - "--model=/mnt/models" |
| - "--served-model-name={{.Name}}" |
| env: |
| - name: HF_HOME |
| value: /tmp/hf_home |
| ports: |
| - containerPort: 8080 |
| protocol: TCP |
| ``` |
|
|
| ```python |
| # Attach model to vllm server. This is an NVIDIA template |
| # Save as: inferenceservice.yaml |
| apiVersion: serving.kserve.io/v1beta1 |
| kind: InferenceService |
| metadata: |
| annotations: |
| openshift.io/display-name: DeepSeek-R1-0528-quantized.w4a16 # OPTIONAL CHANGE |
| serving.kserve.io/deploymentMode: RawDeployment |
| name: DeepSeek-R1-0528-quantized.w4a16 # specify model name. This value will be used to invoke the model in the payload |
| labels: |
| opendatahub.io/dashboard: 'true' |
| spec: |
| predictor: |
| maxReplicas: 1 |
| minReplicas: 1 |
| model: |
| modelFormat: |
| name: vLLM |
| name: '' |
| resources: |
| limits: |
| cpu: '2' # this is model specific |
| memory: 8Gi # this is model specific |
| nvidia.com/gpu: '1' # this is accelerator specific |
| requests: # same comment for this block |
| cpu: '1' |
| memory: 4Gi |
| nvidia.com/gpu: '1' |
| runtime: vllm-cuda-runtime # must match the ServingRuntime name above |
| storageUri: oci://registry.redhat.io/rhelai1/modelcar-deepseek-r1-0528-quantized-w4a16:1.5 |
| tolerations: |
| - effect: NoSchedule |
| key: nvidia.com/gpu |
| operator: Exists |
| ``` |
|
|
| ```bash |
| # make sure first to be in the project where you want to deploy the model |
| # oc project <project-name> |
| |
| # apply both resources to run model |
| |
| # Apply the ServingRuntime |
| oc apply -f vllm-servingruntime.yaml |
| |
| ``` |
|
|
| ```python |
| # Replace <inference-service-name> and <cluster-ingress-domain> below: |
| # - Run `oc get inferenceservice` to find your URL if unsure. |
| |
| # Call the server using curl: |
| curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions |
| -H "Content-Type: application/json" \ |
| -d '{ |
| "model": "DeepSeek-R1-0528-quantized.w4a16", |
| "stream": true, |
| "stream_options": { |
| "include_usage": true |
| }, |
| "max_tokens": 1, |
| "messages": [ |
| { |
| "role": "user", |
| "content": "How can a bee fly when its wings are so small?" |
| } |
| ] |
| }' |
| |
| ``` |
|
|
| See [Red Hat Openshift AI documentation](https://docs.redhat.com/en/documentation/red_hat_openshift_ai/2025) for more details. |
| </details> |
|
|
|
|
| ## Creation |
|
|
| We created this model using **MoE-Quant**, a library developed jointly with **ISTA** and tailored for the quantization of very large Mixture-of-Experts (MoE) models. |
|
|
| For more details, please refer to the [MoE-Quant repository](https://github.com/IST-DASLab/MoE-Quant). |
|
|
|
|
| ## Evaluation |
|
|
| The model was evaluated on popular reasoning tasks (AIME 2024, MATH-500, GPQA-Diamond) via [LightEval](https://github.com/huggingface/open-r1). |
| For reasoning evaluations, we estimate pass@1 based on 10 runs with different seeds, `temperature=0.6`, `top_p=0.95` and `max_new_tokens=65536`. |
|
|
|
|
| ### Accuracy |
|
|
| | | Recovery (%) | deepseek/DeepSeek-R1-0528 | RedHatAI/DeepSeek-R1-0528-quantized.w4a16<br>(this model) | |
| | --------------------------- | :----------: | :------------------: | :--------------------------------------------------: | |
| | AIME 2024<br>pass@1 | 98.50 | 88.66 | 87.33 | |
| | MATH-500<br>pass@1 | 99.88 | 97.52 | 97.40 | |
| | GPQA Diamond<br>pass@1 | 101.21 | 79.65 | 80.61 | |
| | **Reasoning<br>Average Score** | **99.82** | **88.61** | **88.45** | |
