DeepSeek-V3.1-Nex-N1 671B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
DeepSeek V3.1 post-trained by Nex-AGI for agent autonomy and tool use — the base model's 671B weights at the base model's size, so 406 GB at Q4_K_M. Scores 80.2 on tau2-Bench, 70.6 on SWE-bench Verified, 65.3 on BFCL v4 and 29.5 on GAIA2. MLA attention keeps the KV cache small enough for a 128K context at this scale.
DeepSeek-V3.1-Nex-N1 671B 在 Q4_K_M 下约需 406 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 | 222 GB | — | 放不下 | |
| Q3_K_M 3.41 bpw | 287.4 GB | — | 放不下 | |
| Q4_K_M 4.83 bpw | 406.5 GB | — | 放不下 | |
| Q5_K_M 5.67 bpw | 476.9 GB | — | 放不下 | |
| Q6_K 6.56 bpw | 551.6 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 714.3 GB | — | 放不下 | |
| F16 16.00 bpw | 1343.4 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-V3.1-Nex-N1 671B 显存计算器 →
运行 DeepSeek-V3.1-Nex-N1 671B
目录中能运行 DeepSeek-V3.1-Nex-N1 671B 的最便宜 GPU 是 Apple M3 Ultra (512 GB).
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
如何运行 DeepSeek-V3.1-Nex-N1 671B
安装 Ollama，然后运行：
ollama run nex-n1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
- Mixture-of-Experts (DeepSeek V3.1 post-train, MLA attention)
- 提供商
- Nex-AGI
- 许可证
- MIT
- 规格量化
- Q4_K_M
- 系统内存
- 512 GB
- 记录更新于
- 2026-09-08
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-V3.1-Nex-N1 671B 吗？
DeepSeek-V3.1-Nex-N1 671B — 常见问题
How much VRAM does DeepSeek-V3.1-Nex-N1 671B need?
About 406 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-V3.1-Nex-N1 671B run on an RTX 4090 (24 GB)?
No. DeepSeek-V3.1-Nex-N1 671B needs about 406 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-V3.1-Nex-N1 671B locally?
Install Ollama and run `ollama run nex-n1`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.