- Introduction
- Model Summary
- Model Downloads
- Evaluation Results
- Chat Website & API Platform
- How to Run Locally
- License
- Citation
- Contact
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks.
Architecture: Innovative Load Balancing Strategy and Training Objective
- On top of the efficient architecture of DeepSeek-V2, we pioneer an auxiliary-loss-free strategy for load balancing, which minimizes the performance degradation that arises from encouraging load balancing.
- We investigate a Multi-Token Prediction (MTP) objective and prove it beneficial to model performance. It can also be used for speculative decoding for inference acceleration.
Pre-Training: Towards Ultimate Training Efficiency
- We design an FP8 mixed precision training framework and, for the first time, validate the feasibility and effectiveness of FP8 training on an extremely large-scale model.
- Through co-design of algorithms, frameworks, and hardware, we overcome the communication bottleneck in cross-node MoE training, nearly achieving full computation-communication overlap.
This significantly enhances our training efficiency and reduces the training costs, enabling us to further scale up the model size without additional overhead. - At an economical cost of only 2.664M H800 GPU hours, we complete the pre-training of DeepSeek-V3 on 14.8T tokens, producing the currently strongest open-source base model. The subsequent training stages after pre-training require only 0.1M GPU hours.
Post-Training: Knowledge Distillation from DeepSeek-R1
- We introduce an innovative methodology to distill reasoning capabilities from the long-Chain-of-Thought (CoT) model, specifically from one of the DeepSeek R1 series models, into standard LLMs, particularly DeepSeek-V3. Our pipeline elegantly incorporates the verification and reflection patterns of R1 into DeepSeek-V3 and notably improves its reasoning performance. Meanwhile, we also maintain a control over the output style and length of DeepSeek-V3.
| Model | #Total Params | #Activated Params | Context Length | Download |
|---|---|---|---|---|
| DeepSeek-V3-Base | 671B | 37B | 128K | 🤗 Hugging Face |
| DeepSeek-V3 | 671B | 37B | 128K | 🤗 Hugging Face |
Note
The total size of DeepSeek-V3 models on Hugging Face is 685B, which includes 671B of the Main Model weights and 14B of the Multi-Token Prediction (MTP) Module weights.
To ensure optimal performance and flexibility, we have partnered with open-source communities and hardware vendors to provide multiple ways to run the model locally. For step-by-step guidance, check out Section 6: How_to Run_Locally.
For developers looking to dive deeper, we recommend exploring README_WEIGHTS.md for details on the Main Model weights and the Multi-Token Prediction (MTP) Modules. Please note that MTP support is currently under active development within the community, and we welcome your contributions and feedback.
| Benchmark (Metric) | # Shots | DeepSeek-V2 | Qwen2.5 72B | LLaMA3.1 405B | DeepSeek-V3 | |
|---|---|---|---|---|---|---|
| Architecture | - | MoE | Dense | Dense | MoE | |
| # Activated Params | - | 21B | 72B | 405B | 37B | |
| # Total Params | - | 236B | 72B | 405B | 671B | |
| English | Pile-test (BPB) | - | 0.606 | 0.638 | 0.542 | 0.548 |
| BBH (EM) | 3-shot | 78.8 | 79.8 | 82.9 | 87.5 | |
| MMLU (Acc.) | 5-shot | 78.4 | 85.0 | 84.4 | 87.1 | |
| MMLU-Redux (Acc.) | 5-shot | 75.6 | 83.2 | 81.3 | 86.2 | |
| MMLU-Pro (Acc.) | 5-shot | 51.4 | 58.3 | 52.8 | 64.4 | |
| DROP (F1) | 3-shot | 80.4 | 80.6 | 86.0 | 89.0 | |
| ARC-Easy (Acc.) | 25-shot | 97.6 | 98.4 | 98.4 | 98.9 | |
| ARC-Challenge (Acc.) | 25-shot | 92.2 | 94.5 | 95.3 | 95.3 | |
| HellaSwag (Acc.) | 10-shot | 87.1 | 84.8 | 89.2 | 88.9 | |
| PIQA (Acc.) | 0-shot | 83.9 | 82.6 | 85.9 | 84.7 | |
| WinoGrande (Acc.) | 5-shot | 86.3 | 82.3 | 85.2 | 84.9 | |
| RACE-Middle (Acc.) | 5-shot | 73.1 | 68.1 | 74.2 | 67.1 | |
| RACE-High (Acc.) | 5-shot | 52.6 | 50.3 | 56.8 | 51.3 | |
| TriviaQA (EM) | 5-shot | 80.0 | 71.9 | 82.7 | 82.9 | |
| NaturalQuestions (EM) | 5-shot | 38.6 | 33.2 | 41.5 | 40.0 | |
| AGIEval (Acc.) | 0-shot | 57.5 | 75.8 | 60.6 | 79.6 | |
| Code | HumanEval (Pass@1) | 0-shot | 43.3 | 53.0 | 54.9 | 65.2 |
| MBPP (Pass@1) | 3-shot | 65.0 | 72.6 | 68.4 | 75.4 | |
| LiveCodeBench-Base (Pass@1) | 3-shot | 11.6 | 12.9 | 15.5 | 19.4 | |
| CRUXEval-I (Acc.) | 2-shot | 52.5 | 59.1 | 58.5 | 67.3 | |
| CRUXEval-O (Acc.) | 2-shot | 49.8 | 59.9 | 59.9 | 69.8 | |
| Math | GSM8K (EM) | 8-shot | 81.6 | 88.3 | 83.5 | 89.3 |
| MATH (EM) | 4-shot | 43.4 | 54.4 | 49.0 | 61.6 | |
| MGSM (EM) | 8-shot | 63.6 | 76.2 | 69.9 | 79.8 | |
| CMath (EM) | 3-shot | 78.7 | 84.5 | 77.3 | 90.7 | |
| Chinese | CLUEWSC (EM) | 5-shot | 82.0 | 82.5 | 83.0 | 82.7 |
| C-Eval (Acc.) | 5-shot | 81.4 | 89.2 | 72.5 | 90.1 | |
| CMMLU (Acc.) | 5-shot | 84.0 | 89.5 | 73.7 | 88.8 | |
| CMRC (EM) | 1-shot | 77.4 | 75.8 | 76.0 | 76.3 | |
| C3 (Acc.) | 0-shot | 77.4 | 76.7 | 79.7 | 78.6 | |
| CCPM (Acc.) | 0-shot | 93.0 | 88.5 | 78.6 | 92.0 | |
| Multilingual | MMMLU-non-English (Acc.) | 5-shot | 64.0 | 74.8 | 73.8 | 79.4 |
Note
Best results are shown in bold. Scores with a gap not exceeding 0.3 are considered to be at the same level. DeepSeek-V3 achieves the best performance on most benchmarks, especially on math and code tasks. For more evaluation details, please check our paper.
Evaluation results on the Needle In A Haystack (NIAH) tests. DeepSeek-V3 performs well across all context window lengths up to 128K.
| Benchmark (Metric) | DeepSeek V2-0506 | DeepSeek V2.5-0905 | Qwen2.5 72B-Inst. | Llama3.1 405B-Inst. | Claude-3.5-Sonnet-1022 | GPT-4o 0513 | DeepSeek V3 | |
|---|---|---|---|---|---|---|---|---|
| Architecture | MoE | MoE | Dense | Dense | - | - | MoE | |
| # Activated Params | 21B | 21B | 72B | 405B | - | - | 37B | |
| # Total Params | 236B | 236B | 72B | 405B | - | - | 671B | |
| English | MMLU (EM) | 78.2 | 80.6 | 85.3 | 88.6 | 88.3 | 87.2 | 88.5 |
| MMLU-Redux (EM) | 77.9 | 80.3 | 85.6 | 86.2 | 88.9 | 88.0 | 89.1 | |
| MMLU-Pro (EM) | 58.5 | 66.2 | 71.6 | 73.3 | 78.0 | 72.6 | 75.9 | |
| DROP (3-shot F1) | 83.0 | 87.8 | 76.7 | 88.7 | 88.3 | 83.7 | 91.6 | |
| IF-Eval (Prompt Strict) | 57.7 | 80.6 | 84.1 | 86.0 | 86.5 | 84.3 | 86.1 | |
| GPQA-Diamond (Pass@1) | 35.3 | 41.3 | 49.0 | 51.1 | 65.0 | 49.9 | 59.1 | |
| SimpleQA (Correct) | 9.0 | 10.2 | 9.1 | 17.1 | 28.4 | 38.2 | 24.9 | |
| FRAMES (Acc.) | 66.9 | 65.4 | 69.8 | 70.0 | 72.5 | 80.5 | 73.3 | |
| LongBench v2 (Acc.) | 31.6 | 35.4 | 39.4 | 36.1 | 41.0 | 48.1 | 48.7 | |
| Code | HumanEval-Mul (Pass@1) | 69.3 | 77.4 | 77.3 | 77.2 | 81.7 | 80.5 | 82.6 |
| LiveCodeBench (Pass@1-COT) | 18.8 | 29.2 | 31.1 | 28.4 | 36.3 | 33.4 | 40.5 | |
| LiveCodeBench (Pass@1) | 20.3 | 28.4 | 28.7 | 30.1 | 32.8 | 34.2 | 37.6 | |
| Codeforces (Percentile) | 17.5 | 35.6 | 24.8 | 25.3 | 20.3 | 23.6 | 51.6 | |
| SWE Verified (Resolved) | - | 22.6 | 23.8 | 24.5 | 50.8 | 38.8 | 42.0 | |
| Aider-Edit (Acc.) | 60.3 | 71.6 | 65.4 | 63.9 | 84.2 | 72.9 | 79.7 | |
| Aider-Polyglot (Acc.) | - | 18.2 | 7.6 | 5.8 | 45.3 | 16.0 | 49.6 | |
| Math | AIME 2024 (Pass@1) | 4.6 | 16.7 | 23.3 | 23.3 | 16.0 | 9.3 | 39.2 |
| MATH-500 (EM) | 56.3 | 74.7 | 80.0 | 73.8 | 78.3 | 74.6 | 90.2 | |
| CNMO 2024 (Pass@1) | 2.8 | 10.8 | 15.9 | 6.8 | 13.1 | 10.8 | 43.2 | |
| Chinese | CLUEWSC (EM) | 89.9 | 90.4 | 91.4 | 84.7 | 85.4 | 87.9 | 90.9 |
| C-Eval (EM) | 78.6 | 79.5 | 86.1 | 61.5 | 76.7 | 76.0 | 86.5 | |
| C-SimpleQA (Correct) | 48.5 | 54.1 | 48.4 | 50.4 | 51.3 | 59.3 | 64.8 |
Note
All models are evaluated with an output length limit of 8K tokens. Benchmarks with fewer than 1000 samples are tested multiple times with varying temperature settings to ensure robust results. DeepSeek-V3 stands out as the top-performing open-source model and demonstrates competitive performance against leading closed-source models.
Below is a table showcasing DeepSeek-V3's performance in open-ended generation tasks compared to other models:
| Model | Arena-Hard | AlpacaEval 2.0 |
|---|---|---|
| DeepSeek-V2.5-0905 | 76.2 | 50.5 |
| Qwen2.5-72B-Instruct | 81.2 | 49.1 |
| LLaMA-3.1 405B | 69.3 | 40.5 |
| GPT-4o-0513 | 80.4 | 51.1 |
| Claude-Sonnet-3.5-1022 | 85.2 | 52.0 |
| DeepSeek-V3 | 85.5 | 70.0 |
Note
Evaluations were conducted on open-ended English conversation tasks. For AlpacaEval 2.0, the length-controlled win rate is used as the metric.
DeepSeek-V3 consistently excels in these tests, outperforming in both structured and open-ended generation tasks.
You can interact with DeepSeek-V3 through the following platforms:
- Chat Website: Try DeepSeek-V3 directly on the official platform: chat.deepseek.com
- API Platform: Integrate DeepSeek-V3 into your applications with our OpenAI-compatible API: platform.deepseek.com
DeepSeek-V3 can be deployed locally using various open-source tools and hardware configurations. Below are the supported methods and requirements:
- DeepSeek-Infer Demo: A lightweight demo for FP8 and BF16 inference.
- SGLang: Full support for BF16 and FP8 inference, with multi-token prediction in development.
- LMDeploy: Efficient FP8 and BF16 inference for local and cloud deployments.
- TensorRT-LLM: Supports BF16 inference and INT4/8 quantization; FP8 support is coming soon.
- vLLM: Compatible with FP8 and BF16 modes, offering tensor and pipeline parallelism.
- AMD GPU: Run DeepSeek-V3 on AMD GPUs via SGLang in BF16 and FP8 modes.
- Huawei Ascend NPU: Compatible with Huawei Ascend devices.
Note
Since DeepSeek-V3 was trained with FP8 precision, only FP8 weights are provided. To use BF16 weights, convert them using this script:
cd inference
python fp8_cast_bf16.py --input-fp8-hf-path /path/to/fp8_weights --output-bf16-hf-path /path/to/bf16_weights System Requirements:
- Linux with Python 3.10 (Mac and Windows are not supported).
- Dependencies:
pip install torch==2.4.1 triton==3.0.0 transformers==4.46.3 safetensors==0.4.5
git clone https://github.com/deepseek-ai/DeepSeek-V3.git
cd DeepSeek-V3/inference
pip install -r requirements.txt
python convert.py --hf-ckpt-path /path/to/DeepSeek-V3 --save-path /path/to/DeepSeek-V3-Demo --n-experts 256 --model-parallel 16
torchrun --nnodes 2 --nproc-per-node 8 --node-rank $RANK --master-addr $ADDR generate.py --ckpt-path /path/to/DeepSeek-V3-Demo --config configs/config_671B.json --interactive --temperature 0.7 --max-new-tokens 200
torchrun --nnodes 2 --nproc-per-node 8 --node-rank $RANK --master-addr $ADDR generate.py --ckpt-path /path/to/DeepSeek-V3-Demo --config configs/config_671B.json --input-file $FILE
@misc{deepseekai2024deepseekv3technicalreport,
title={DeepSeek-V3 Technical Report},
author={DeepSeek-AI},
year={2024},
eprint={2412.19437},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2412.19437},
}
This is ready to be copied and pasted directly into your project’s Markdown file, maintaining proper formatting and structure. Let me know if you need further adjustments!