🤗 unsloth/DeepSeek-V4-Flash-GGUF —— 高效百万 Token 上下文智能模型
英文标题：🤗 unsloth/DeepSeek-V4-Flash-GGUF
DeepSeek-V4 系列发布，包含 1.6T 参数的 DeepSeek-V4-Pro 与 284B 参数的 DeepSeek-V4-Flash，均支持百万 Token 上下文。Flash 版仅 13B 激活参数，采用混合注意力、mHC 与 Muon 优化器，在多项基准中表现强劲。Pro-Max 模式显著拉近与顶级闭源模型的差距，并在代码与代理任务中达到开源最佳。Unsloth 提供 GGUF 量化与 Unsloth Studio 支持，开发者可快速本地部署并体验高/最大思考模式。
4.5 KB
4.9 KB
31.0 KB
14.9 KB
12.2 KB
759.9 KB
10.4 KB
6.0 KB
1.3 KB
1.3 KB
1.8 KB
1.3 KB
409.4 KB
中文
要正确运行 DeepSeek-V4，请确保使用最新版本的 llama.cpp 或 Unsloth Studio。 我们还改进了 DeepSeek-V4 的聊天 jinja 模板，并测试了超过 4000 轮对话，确保与官方基线一致。
Unsloth Dynamic 2.0 实现了卓越的精度，并超越了其他领先的量化方案。
- 要以全精度无损方式运行 DeepSeek-V4-Flash，请使用 Q8（UD-Q8_K_XL），大小为 162GB，仅比 Q4（UD-Q4_K_XL）大 7GB。
- 有关量化分析和说明，请参阅我们的 DeepSeek-V4 指南。
- 您现在可以在 Unsloth Studio 中运行 DeepSeek-V4-Flash，并提供 High 和 Max 思考模式切换。
DeepSeek-V4：面向高效百万 Token 上下文智能
引言
我们发布 DeepSeek-V4 系列的预览版本，包括两个强大的混合专家（MoE）语言模型——DeepSeek-V4-Pro（1.6T 参数，49B 激活）和 DeepSeek-V4-Flash（284B 参数，13B 激活）——两者均支持百万 token 的上下文长度。
DeepSeek-V4 系列在架构与优化方面引入了若干关键升级：
- 混合注意力架构： 我们设计了一种结合压缩稀疏注意力（CSA）与重度压缩注意力（HCA）的混合注意力机制，大幅提升长上下文效率。在百万 token 上下文下，DeepSeek-V4-Pro 的单 token 推理 FLOPs 仅为 DeepSeek-V3.2 的 27%，KV 缓存为 10%。
- 流形约束超连接（mHC）： 引入 mHC 以增强传统残差连接，在保持模型表达能力的同时提升层间信号传播的稳定性。
- Muon 优化器： 采用 Muon 优化器，实现更快的收敛和更高的训练稳定性。
我们使用超过 32T 多样化高质量 token 对两个模型进行预训练，随后进行了全面的后训练流程。后训练采用两阶段范式：独立培养领域专家（通过 SFT 与基于 GRPO 的强化学习），然后通过在线策略蒸馏进行统一模型整合，将不同领域的专长融入单一模型。
DeepSeek-V4-Pro-Max 作为 DeepSeek-V4-Pro 的最大推理努力模式，显著提升了开源模型的知识能力，确立了当今最佳开源模型的地位。它在编码基准上取得顶尖表现，并在推理与代理任务上大幅缩小了与领先闭源模型的差距。同时，DeepSeek-V4-Flash-Max 在获得更大思考预算时，可实现与 Pro 版本相当的推理性能，尽管其较小的参数规模使其在纯知识任务和最复杂的代理工作流中略逊一筹。
模型下载
*FP4 + FP8 混合：MoE 专家参数使用 FP4 精度；其他大多数参数使用 FP8。
评测结果
基座模型
| 基准测试（指标） | 样本数 | DeepSeek-V3.2-Base | DeepSeek-V4-Flash-Base | DeepSeek-V4-Pro-Base |
|---|---|---|---|---|
| 架构 | - | MoE | MoE | MoE |
| 激活参数量 | - | 37B | 13B | 49B |
| 总参数量 | - | 671B | 284B | 1.6T |
| 世界知识 | ||||
| AGIEval (EM) | 0-shot | 80.1 | 82.6 | 83.1 |
| MMLU (EM) | 5-shot | 87.8 | 88.7 | 90.1 |
| MMLU-Redux (EM) | 5-shot | 87.5 | 89.4 | 90.8 |
| MMLU-Pro (EM) | 5-shot | 65.5 | 68.3 | 73.5 |
| MMMLU (EM) | 5-shot | 87.9 | 88.8 | 90.3 |
| C-Eval (EM) | 5-shot | 90.4 | 92.1 | 93.1 |
| CMMLU (EM) | 5-shot | 88.9 | 90.4 | 90.8 |
| MultiLoKo (EM) | 5-shot | 38.7 | 42.2 | 51.1 |
| Simple-QA verified (EM) | 25-shot | 28.3 | 30.1 | 55.2 |
| SuperGPQA (EM) | 5-shot | 45.0 | 46.5 | 53.9 |
| FACTS Parametric (EM) | 25-shot | 27.1 | 33.9 | 62.6 |
| TriviaQA (EM) | 5-shot | 83.3 | 82.8 | 85.6 |
| 语言与推理 | ||||
| BBH (EM) | 3-shot | 87.6 | 86.9 | 87.5 |
| DROP (F1) | 1-shot | 88.2 | 88.6 | 88.7 |
| HellaSwag (EM) | 0-shot | 86.4 | 85.7 | 88.0 |
| WinoGrande (EM) | 0-shot | 78.9 | 79.5 | 81.5 |
| CLUEWSC (EM) | 5-shot | 83.5 | 82.2 | 85.2 |
| 代码与数学 | ||||
| BigCodeBench (Pass@1) | 3-shot | 63.9 | 56.8 | 59.2 |
| HumanEval (Pass@1) | 0-shot | 62.8 | 69.5 | 76.8 |
| GSM8K (EM) | 8-shot | 91.1 | 90.8 | 92.6 |
| MATH (EM) | 4-shot | 60.5 | 57.4 | 64.5 |
| MGSM (EM) | 8-shot | 81.3 | 85.7 | 84.4 |
| CMath (EM) | 3-shot | 92.6 | 93.6 | 90.9 |
| 长上下文 | ||||
| LongBench-V2 (EM) | 1-shot | 40.2 | 44.7 | 51.5 |
指令模型
DeepSeek-V4-Pro 与 DeepSeek-V4-Flash 均支持三种推理努力模式：
| 推理模式 | 特点 | 典型用例 | 回复格式 |
|---|---|---|---|
| Non-think | 快速、直觉式回应 | 日常常规任务、低风险决策 | </think> 摘要 |
| Think High | 有意识逻辑分析，较慢但更准确 | 复杂问题解决、规划 | <think> 思考 </think> 摘要 |
| Think Max | 将推理推至极限 | 探索模型推理能力的边界 | 特殊系统提示 + <think> 思考 </think> 摘要 |
DeepSeek-V4-Pro-Max 与前沿模型对比
| 基准测试（指标） | Opus-4.6 Max | GPT-5.4 xHigh | Gemini-3.1-Pro High | K2.6 Thinking | GLM-5.1 Thinking | DS-V4-Pro Max |
|---|---|---|---|---|---|---|
| 知识与推理 | ||||||
| MMLU-Pro (EM) | 89.1 | 87.5 | 91.0 | 87.1 | 86.0 | 87.5 |
| SimpleQA-Verified (Pass@1) | 46.2 | 45.3 | 75.6 | 36.9 | 38.1 | 57.9 |
| Chinese-SimpleQA (Pass@1) | 76.4 | 76.8 | 85.9 | 75.9 | 75.0 | 84.4 |
| GPQA Diamond (Pass@1) | 91.3 | 93.0 | 94.3 | 90.5 | 86.2 | 90.1 |
| HLE (Pass@1) | 40.0 | 39.8 | 44.4 | 36.4 | 34.7 | 37.7 |
| LiveCodeBench (Pass@1) | 88.8 | - | 91.7 | 89.6 | - | 93.5 |
| Codeforces (Rating) | - | 3168 | 3052 | - | - | 3206 |
| HMMT 2026 Feb (Pass@1) | 96.2 | 97.7 | 94.7 | 92.7 | 89.4 | 95.2 |
| IMOAnswerBench (Pass@1) | 75.3 | 91.4 | 81.0 | 86.0 | 83.8 | 89.8 |
| Apex (Pass@1) | 34.5 | 54.1 | 60.9 | 24.0 | 11.5 | 38.3 |
| Apex Shortlist (Pass@1) | 85.9 | 78.1 | 89.1 | 75.5 | 72.4 | 90.2 |
| 长上下文 | ||||||
| MRCR 1M (MMR) | 92.9 | - | 76.3 | - | - | 83.5 |
| CorpusQA 1M (ACC) | 71.7 | - | 53.8 | - | - | 62.0 |
| 代理 | ||||||
| Terminal Bench 2.0 (Acc) | 65.4 | 75.1 | 68.5 | 66.7 | 63.5 | 67.9 |
| SWE Verified (Resolved) | 80.8 | - | 80.6 | 80.2 | - | 80.6 |
| SWE Pro (Resolved) | 57.3 | 57.7 | 54.2 | 58.6 | 58.4 | 55.4 |
| SWE Multilingual (Resolved) | 77.5 | - | - | 76.7 | 73.3 | 76.2 |
| BrowseComp (Pass@1) | 83.7 | 82.7 | 85.9 | 83.2 | 79.3 | 83.4 |
| HLE w/ tools (Pass@1) | 53.1 | 52.0 | 51.6 | 54.0 | 50.4 | 48.2 |
| GDPval-AA (Elo) | 1619 | 1674 | 1314 | 1482 | 1535 | 1554 |
| MCPAtlas Public (Pass@1) | 73.8 | 67.2 | 69.2 | 66.6 | 71.8 | 73.6 |
| Toolathlon (Pass@1) | 47.2 | 54.6 | 48.8 | 50.0 | 40.7 | 51.8 |
不同推理模式对比
| 基准测试（指标） | V4-Flash Non-Think | V4-Flash High | V4-Flash Max | V4-Pro Non-Think | V4-Pro High | V4-Pro Max |
|---|---|---|---|---|---|---|
| 知识与推理 | ||||||
| MMLU-Pro (EM) | 83.0 | 86.4 | 86.2 | 82.9 | 87.1 | 87.5 |
| SimpleQA-Verified (Pass@1) | 23.1 | 28.9 | 34.1 | 45.0 | 46.2 | 57.9 |
| Chinese-SimpleQA (Pass@1) | 71.5 | 73.2 | 78.9 | 75.8 | 77.7 | 84.4 |
| GPQA Diamond (Pass@1) | 71.2 | 87.4 | 88.1 | 72.9 | 89.1 | 90.1 |
| HLE (Pass@1) | 8.1 | 29.4 | 34.8 | 7.7 | 34.5 | 37.7 |
| LiveCodeBench (Pass@1) | 55.2 | 88.4 | 91.6 | 56.8 | 89.8 | 93.5 |
| Codeforces (Rating) | - | 2816 | 3052 | - | 2919 | 3206 |
| HMMT 2026 Feb (Pass@1) | 40.8 | 91.9 | 94.8 | 31.7 | 94.0 | 95.2 |
| IMOAnswerBench (Pass@1) | 41.9 | 85.1 | 88.4 | 35.3 | 88.0 | 89.8 |
| Apex (Pass@1) | 1.0 | 19.1 | 33.0 | 0.4 | 27.4 | 38.3 |
| Apex Shortlist (Pass@1) | 9.3 | 72.1 | 85.7 | 9.2 | 85.5 | 90.2 |
| 长上下文 | ||||||
| MRCR 1M (MMR) | 37.5 | 76.9 | 78.7 | 44.7 | 83.3 | 83.5 |
| CorpusQA 1M (ACC) | 15.5 | 59.3 | 60.5 | 35.6 | 56.5 | 62.0 |
| 代理 | ||||||
| Terminal Bench 2.0 (Acc) | 49.1 | 56.6 | 56.9 | 59.1 | 63.3 | 67.9 |
| SWE Verified (Resolved) | 73.7 | 78.6 | 79.0 | 73.6 | 79.4 | 80.6 |
| SWE Pro (Resolved) | 49.1 | 52.3 | 52.6 | 52.1 | 54.4 | 55.4 |
| SWE Multilingual (Resolved) | 69.7 | 70.2 | 73.3 | 69.8 | 74.1 | 76.2 |
| BrowseComp (Pass@1) | - | 53.5 | 73.2 | - | 80.4 | 83.4 |
| HLE w/ tools (Pass@1) | - | 40.3 | 45.1 | - | 44.7 | 48.2 |
| MCPAtlas (Pass@1) | 64.0 | 67.4 | 69.0 | 69.4 | 74.2 | 73.6 |
| GDPval-AA (Elo) | - | - | 1395 | - | - | 1554 |
| Toolathlon (Pass@1) | 40.7 | 43.5 | 47.8 | 46.3 | 49.0 | 51.8 |
聊天模板
本次发布不包含 Jinja 格式的聊天模板。取而代之，我们提供了一个专门的 encoding 文件夹，内含 Python 脚本与测试用例，演示如何将符合 OpenAI 兼容格式的消息编码为模型的输入字符串，以及如何解析模型的文本输出。完整文档请参阅 encoding 文件夹。
简要示例：
python from encoding_dsv4 import encode_messages, parse_message_from_completion_text
messages = [ {"role": "user", "content": "hello"}, {"role": "assistant", "content": "Hello! I am DeepSeek.", "reasoning_content": "thinking..."}, {"role": "user", "content": "1+1=?"} ]
prompt = encode_messages(messages, thinking_mode="thinking")
import transformers tokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Pro") tokens = tokenizer.encode(prompt)
本地运行
关于如何在本地运行 DeepSeek-V4，包括模型权重转换与交互式聊天演示，请参阅 推理 文件夹中的详细说明。
对于本地部署，我们建议将采样参数设为 temperature = 1.0, top_p = 1.0。对于 Think Max 推理模式，建议将上下文窗口设置为至少 384K token。
许可证
本仓库及模型权重基于 MIT 许可证 授权。
引用
bibtex @misc{deepseekai2026deepseekv4, title={DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence}, author={DeepSeek-AI}, year={2026}, }
联系
如有任何问题，请提交 issue 或通过 service@deepseek.com 联系我们。
English / 原文
To run DeepSeek-V4 correctly, ensure you use the latest version of llama.cpp or Unsloth Studio.
We also improved the DeepSeek-V4 chat jinja template, and tested over 4000 conversations to be equivalent with the official baseline.
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.
- To run DeepSeek-V4-Flash in full precision lossless, run Q8 (UD-Q8_K_XL), which is 162GB and only 7GB bigger than Q4 (UD-Q4_K_XL).
- See our DeepSeek-V4 guide for quantization analysis and instructions.
- You can now run DeepSeek-V4-Flash in Unsloth Studio with toggles for High and Max thinking.
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
Introduction
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.
DeepSeek-V4 series incorporate several key upgrades in architecture and optimization:
- Hybrid Attention Architecture: We design a hybrid attention mechanism combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to dramatically improve long-context efficiency. In the 1M-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2.
- Manifold-Constrained Hyper-Connections (mHC): We incorporate mHC to strengthen conventional residual connections, enhancing stability of signal propagation across layers while preserving model expressivity.
- Muon Optimizer: We employ the Muon optimizer for faster convergence and greater training stability.
We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline. The post-training features a two-stage paradigm: independent cultivation of domain-specific experts (through SFT and RL with GRPO), followed by unified model consolidation via on-policy distillation, integrating distinct proficiencies across diverse domains into a single model.
DeepSeek-V4-Pro-Max , the maximum reasoning effort mode of DeepSeek-V4-Pro, significantly advances the knowledge capabilities of open-source models, firmly establishing itself as the best open-source model available today. It achieves top-tier performance in coding benchmarks and significantly bridges the gap with leading closed-source models on reasoning and agentic tasks. Meanwhile, DeepSeek-V4-Flash-Max achieves comparable reasoning performance to the Pro version when given a larger thinking budget, though its smaller parameter scale naturally places it slightly behind on pure knowledge tasks and the most complex agentic workflows.
Model Downloads
*FP4 + FP8 Mixed: MoE expert parameters use FP4 precision; most other parameters use FP8.
Evaluation Results
Base Model
| Benchmark (Metric) | # Shots | DeepSeek-V3.2-Base | DeepSeek-V4-Flash-Base | DeepSeek-V4-Pro-Base |
|---|---|---|---|---|
| Architecture | - | MoE | MoE | MoE |
Activated Params | - | 37B | 13B | 49B
Total Params | - | 671B | 284B | 1.6T
World Knowledge | | | |
AGIEval (EM) | 0-shot | 80.1 | 82.6 | 83.1
MMLU (EM) | 5-shot | 87.8 | 88.7 | 90.1
MMLU-Redux (EM) | 5-shot | 87.5 | 89.4 | 90.8
MMLU-Pro (EM) | 5-shot | 65.5 | 68.3 | 73.5
MMMLU (EM) | 5-shot | 87.9 | 88.8 | 90.3
C-Eval (EM) | 5-shot | 90.4 | 92.1 | 93.1
CMMLU (EM) | 5-shot | 88.9 | 90.4 | 90.8
MultiLoKo (EM) | 5-shot | 38.7 | 42.2 | 51.1
Simple-QA verified (EM) | 25-shot | 28.3 | 30.1 | 55.2
SuperGPQA (EM) | 5-shot | 45.0 | 46.5 | 53.9
FACTS Parametric (EM) | 25-shot | 27.1 | 33.9 | 62.6
TriviaQA (EM) | 5-shot | 83.3 | 82.8 | 85.6
Language & Reasoning | | | |
BBH (EM) | 3-shot | 87.6 | 86.9 | 87.5
DROP (F1) | 1-shot | 88.2 | 88.6 | 88.7
HellaSwag (EM) | 0-shot | 86.4 | 85.7 | 88.0
WinoGrande (EM) | 0-shot | 78.9 | 79.5 | 81.5
CLUEWSC (EM) | 5-shot | 83.5 | 82.2 | 85.2
Code & Math | | | |
BigCodeBench (Pass@1) | 3-shot | 63.9 | 56.8 | 59.2
HumanEval (Pass@1) | 0-shot | 62.8 | 69.5 | 76.8
GSM8K (EM) | 8-shot | 91.1 | 90.8 | 92.6
MATH (EM) | 4-shot | 60.5 | 57.4 | 64.5
MGSM (EM) | 8-shot | 81.3 | 85.7 | 84.4
CMath (EM) | 3-shot | 92.6 | 93.6 | 90.9
Long Context | | | |
LongBench-V2 (EM) | 1-shot | 40.2 | 44.7 | 51.5
Instruct Model
DeepSeek-V4-Pro and DeepSeek-V4-Flash both support three reasoning effort modes:
| Reasoning Mode | Characteristics | Typical Use Cases | Response Format |
|---|---|---|---|
| Non-think | Fast, intuitive responses | Routine daily tasks, low-risk decisions | </think> summary |
| Think High | Conscious logical analysis, slower but more accurate | Complex problem-solving, planning | <think> thinking </think> summary |
| Think Max | Push reasoning to its fullest extent | Exploring the boundary of model reasoning capability | Special system prompt + <think> thinking </think> summary |
DeepSeek-V4-Pro-Max vs Frontier Models
| Benchmark (Metric) | Opus-4.6 Max | GPT-5.4 xHigh | Gemini-3.1-Pro High | K2.6 Thinking | GLM-5.1 Thinking | DS-V4-Pro Max |
|---|---|---|---|---|---|---|
| Knowledge & Reasoning | ||||||
| MMLU-Pro (EM) | 89.1 | 87.5 | 91.0 | 87.1 | 86.0 | 87.5 |
| SimpleQA-Verified (Pass@1) | 46.2 | 45.3 | 75.6 | 36.9 | 38.1 | 57.9 |
| Chinese-SimpleQA (Pass@1) | 76.4 | 76.8 | 85.9 | 75.9 | 75.0 | 84.4 |
| GPQA Diamond (Pass@1) | 91.3 | 93.0 | 94.3 | 90.5 | 86.2 | 90.1 |
| HLE (Pass@1) | 40.0 | 39.8 | 44.4 | 36.4 | 34.7 | 37.7 |
| LiveCodeBench (Pass@1) | 88.8 | - | 91.7 | 89.6 | - | 93.5 |
| Codeforces (Rating) | - | 3168 | 3052 | - | - | 3206 |
| HMMT 2026 Feb (Pass@1) | 96.2 | 97.7 | 94.7 | 92.7 | 89.4 | 95.2 |
| IMOAnswerBench (Pass@1) | 75.3 | 91.4 | 81.0 | 86.0 | 83.8 | 89.8 |
| Apex (Pass@1) | 34.5 | 54.1 | 60.9 | 24.0 | 11.5 | 38.3 |
| Apex Shortlist (Pass@1) | 85.9 | 78.1 | 89.1 | 75.5 | 72.4 | 90.2 |
| Long Context | ||||||
| MRCR 1M (MMR) | 92.9 | - | 76.3 | - | - | 83.5 |
| CorpusQA 1M (ACC) | 71.7 | - | 53.8 | - | - | 62.0 |
| Agentic | ||||||
| Terminal Bench 2.0 (Acc) | 65.4 | 75.1 | 68.5 | 66.7 | 63.5 | 67.9 |
| SWE Verified (Resolved) | 80.8 | - | 80.6 | 80.2 | - | 80.6 |
| SWE Pro (Resolved) | 57.3 | 57.7 | 54.2 | 58.6 | 58.4 | 55.4 |
| SWE Multilingual (Resolved) | 77.5 | - | - | 76.7 | 73.3 | 76.2 |
| BrowseComp (Pass@1) | 83.7 | 82.7 | 85.9 | 83.2 | 79.3 | 83.4 |
| HLE w/ tools (Pass@1) | 53.1 | 52.0 | 51.6 | 54.0 | 50.4 | 48.2 |
| GDPval-AA (Elo) | 1619 | 1674 | 1314 | 1482 | 1535 | 1554 |
| MCPAtlas Public (Pass@1) | 73.8 | 67.2 | 69.2 | 66.6 | 71.8 | 73.6 |
| Toolathlon (Pass@1) | 47.2 | 54.6 | 48.8 | 50.0 | 40.7 | 51.8 |
Comparison across Modes
| Benchmark (Metric) | V4-Flash Non-Think | V4-Flash High | V4-Flash Max | V4-Pro Non-Think | V4-Pro High | V4-Pro Max |
|---|---|---|---|---|---|---|
| Knowledge & Reasoning | ||||||
| MMLU-Pro (EM) | 83.0 | 86.4 | 86.2 | 82.9 | 87.1 | 87.5 |
| SimpleQA-Verified (Pass@1) | 23.1 | 28.9 | 34.1 | 45.0 | 46.2 | 57.9 |
| Chinese-SimpleQA (Pass@1) | 71.5 | 73.2 | 78.9 | 75.8 | 77.7 | 84.4 |
| GPQA Diamond (Pass@1) | 71.2 | 87.4 | 88.1 | 72.9 | 89.1 | 90.1 |
| HLE (Pass@1) | 8.1 | 29.4 | 34.8 | 7.7 | 34.5 | 37.7 |
| LiveCodeBench (Pass@1) | 55.2 | 88.4 | 91.6 | 56.8 | 89.8 | 93.5 |
| Codeforces (Rating) | - | 2816 | 3052 | - | 2919 | 3206 |
| HMMT 2026 Feb (Pass@1) | 40.8 | 91.9 | 94.8 | 31.7 | 94.0 | 95.2 |
| IMOAnswerBench (Pass@1) | 41.9 | 85.1 | 88.4 | 35.3 | 88.0 | 89.8 |
| Apex (Pass@1) | 1.0 | 19.1 | 33.0 | 0.4 | 27.4 | 38.3 |
| Apex Shortlist (Pass@1) | 9.3 | 72.1 | 85.7 | 9.2 | 85.5 | 90.2 |
| Long Context | ||||||
| MRCR 1M (MMR) | 37.5 | 76.9 | 78.7 | 44.7 | 83.3 | 83.5 |
| CorpusQA 1M (ACC) | 15.5 | 59.3 | 60.5 | 35.6 | 56.5 | 62.0 |
| Agentic | ||||||
| Terminal Bench 2.0 (Acc) | 49.1 | 56.6 | 56.9 | 59.1 | 63.3 | 67.9 |
| SWE Verified (Resolved) | 73.7 | 78.6 | 79.0 | 73.6 | 79.4 | 80.6 |
| SWE Pro (Resolved) | 49.1 | 52.3 | 52.6 | 52.1 | 54.4 | 55.4 |
| SWE Multilingual (Resolved) | 69.7 | 70.2 | 73.3 | 69.8 | 74.1 | 76.2 |
| BrowseComp (Pass@1) | - | 53.5 | 73.2 | - | 80.4 | 83.4 |
| HLE w/ tools (Pass@1) | - | 40.3 | 45.1 | - | 44.7 | 48.2 |
| MCPAtlas (Pass@1) | 64.0 | 67.4 | 69.0 | 69.4 | 74.2 | 73.6 |
| GDPval-AA (Elo) | - | - | 1395 | - | - | 1554 |
| Toolathlon (Pass@1) | 40.7 | 43.5 | 47.8 | 46.3 | 49.0 | 51.8 |
Chat Template
This release does not include a Jinja-format chat template. Instead, we provide a dedicated encoding folder with Python scripts and test cases demonstrating how to encode messages in OpenAI-compatible format into input strings for the model, and how to parse the model's text output. Please refer to the encoding folder for full documentation.
A brief example:
from encoding_dsv4 import encode_messages, parse_message_from_completion_text
messages = [
{"role": "user", "content": "hello"},
{"role": "assistant", "content": "Hello! I am DeepSeek.", "reasoning_content": "thinking..."},
{"role": "user", "content": "1+1=?"}
]
prompt = encode_messages(messages, thinking_mode="thinking")
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Pro")
tokens = tokenizer.encode(prompt)
How to Run Locally
Please refer to the inference folder for detailed instructions on running DeepSeek-V4 locally, including model weight conversion and interactive chat demos.
For local deployment, we recommend setting the sampling parameters to temperature = 1.0, top_p = 1.0. For the Think Max reasoning mode, we recommend setting the context window to at least 384K tokens.
License
This repository and the model weights are licensed under the MIT License.
Citation
@misc{deepseekai2026deepseekv4,
title={DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence},
author={DeepSeek-AI},
year={2026},
}
Contact
If you have any questions, please raise an issue or contact us at service@deepseek.com.