DeepSeek V3.2 671B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
671B MoE with 37B active parameters. Improved over V3 with better tool-use, function-calling, and long-context handling. MIT licensed. DEPRECATED: superseded by DeepSeek V4 (1M context, MIT) — reported retiring 2026-07-24.
DeepSeek V3.2 671B 在 Q4_K_M 下约需 414 GB 显存——量化权重加框架开销，不含 KV 缓存。在 Apple Silicon 上，这部分来自统一内存。
按量化级别的显存与速度
计算基准：NVIDIA RTX 4090 (24 GB)。包含 8K 上下文的 KV 缓存，因此数值高于上方的主数字。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 226.6 GB | — | 放不下 | |
| Q3_K_M 3.41 bpw | 293.4 GB | — | 放不下 | |
| Q4_K_M 4.83 bpw | 414.9 GB | — | 放不下 | |
| Q5_K_M 5.67 bpw | 486.9 GB | — | 放不下 | |
| Q6_K 6.56 bpw | 563.1 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 729.2 GB | — | 放不下 | |
| F16 16.00 bpw | 1371.4 GB | — | 放不下 |
黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型，详见 方法说明页. DeepSeek V3.2 671B 显存计算器 →
运行 DeepSeek V3.2 671B
DeepSeek V3.2 671B is not practical on a single consumer GPU: it needs about 414.4 GB at Q4_K_M, more than any single device in our catalogue holds with headroom. How multi-GPU inference works, or rent a multi-GPU server by the hour:
如何运行 DeepSeek V3.2 671B
安装 Ollama，然后运行：
ollama run deepseek-v3.2:671b-q4规格
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- 参数量
- 671 Billion (37B active)
- 上下文窗口
- 128,000
- 架构
- MoE
- 提供商
- DeepSeek
- 许可证
- MIT
- Practical deployment
- Multi-GPU server
- 规格量化
- Q4_K_M
- 系统内存
- 256 GB
- 记录更新于
- 2026-02-28
Commercial use permitted. No usage restrictions beyond attribution.
质量与使用场景
评分由模型作者或独立评测方发布——衡量质量而非吞吐量，并非我们实测。
我的 GPU 能运行 DeepSeek V3.2 671B 吗？
DeepSeek V3.2 671B — 常见问题
How much VRAM does DeepSeek V3.2 671B need?
About 414 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does DeepSeek V3.2 671B run on an RTX 4090 (24 GB)?
No. DeepSeek V3.2 671B needs about 414 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run DeepSeek V3.2 671B locally?
Install Ollama and run `ollama run deepseek-v3.2:671b-q4`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does DeepSeek V3.2 come in?
DeepSeek V3.2 671B (414 GB), DeepSeek V3.2 685B (414 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.