DeepSeek V4 Pro (Withdrawn Listings) — DeepSeek 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Rank #1 open-weight model on every major benchmark. DeepSeek V4 Pro uses a massive 1.6 trillion parameter Mixture-of-Experts architecture with only 49 billion parameters active per token — giving frontier-tier intelligence at a fraction of the compute cost. Dominates coding, math, reasoning, and multilingual tasks.
变体
DeepSeek V4 Pro (Withdrawn Listings) 最小的变体在 Q4_K_M 下约需 967 GB 显存——量化权重加框架开销，不含 KV 缓存。
| 模型 | Q4 下显存 | 显存 | 上下文 | 运行 |
|---|---|---|---|---|
| DeepSeek V4 Pro (Q4_K_M) 1.6T / 49B active | ~966.8 GB | 128,000 | ollama run deepseek-v4-pro:latest | |
| DeepSeek V4 Pro (API) API | ~966.8 GB | 128,000 | ollama run deepseek-v4-pro |
显存为 Q4_K_M 下的量化权重加开销，与 GPU 与显存检测器使用同一引擎计算。
如何在本地运行 DeepSeek V4 Pro (Withdrawn Listings)
安装 Ollama，然后拉取标签。
ollama run deepseek-v4-pro:latest在上方选择一个尺寸，查看它自己的显存、速度估算和安装命令。
许可证
Research / non-commercial only — this licence does NOT permit shipping a commercial product.
适用于: DeepSeek V4 Pro (Q4_K_M)No downloadable weights. Available through the vendor’s API only.
适用于: DeepSeek V4 Pro (API)DeepSeek V4 Pro (Withdrawn Listings) — 常见问题
How much VRAM does DeepSeek V4 Pro (Withdrawn Listings) need?
DeepSeek V4 Pro (Withdrawn Listings) needs about 967 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: DeepSeek V4 Pro (Q4_K_M) (967 GB, Q4_K_M); DeepSeek V4 Pro (API) (967 GB, None (cloud)). On Apple Silicon, unified memory counts toward this requirement.
Can I run DeepSeek V4 Pro (Withdrawn Listings) on an RTX 4090 (24 GB)?
DeepSeek V4 Pro (Withdrawn Listings)'s smallest variant needs about 967 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for DeepSeek V4 Pro (Withdrawn Listings)?
Q4_K_M is the best balance of quality and VRAM for DeepSeek V4 Pro (Withdrawn Listings) in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run DeepSeek V4 Pro (Withdrawn Listings) with Ollama?
Install Ollama, then run: ollama run deepseek-v4-pro:latest. This downloads DeepSeek V4 Pro (Withdrawn Listings) and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.