Apertus 70B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
The flagship Apertus. At Q4 it needs a 48 GB card or a large-memory unified machine.
Apertus 70B 在 Q4_K_M 下约需 43 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)。仅含权重与开销：该模型架构未公开，因此未计入 KV 缓存。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 23.8 GB | ~29 tok/s | 勉强 | |
| Q3_K_M 3.41 bpw | 30.6 GB | ~3 tok/s | 需卸载 | |
| Q4_K_M 4.83 bpw | 43.1 GB | ~3 tok/s | 需卸载 | |
| Q5_K_M 5.67 bpw | 50.4 GB | ~2 tok/s | 需卸载 | |
| Q6_K 6.56 bpw | 58.2 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 75.2 GB | — | 放不下 | |
| F16 16.00 bpw | 140.8 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. Apertus 70B 显存计算器 →
运行 Apertus 70B
目录中能运行 Apertus 70B 的最便宜 GPU 是 NVIDIA DGX Spark (128 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 Apertus 70B
安装 Ollama，然后运行：
ollama run apertus规格
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed. 尚未确认： context, releaseDate, hfModelId.
- 参数量
- 70 Billion
- 上下文窗口
- 65,536
- 架构
- Dense
- 提供商
- EPFL / ETH Zurich / CSCS
- 许可证
- Apache 2.0
- Practical deployment
- Workstation (large unified memory or pro GPU)
- 规格量化
- Q4_K_M
- 系统内存
- 64 GB
- 记录更新于
- 2026-09-19
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。
Apertus 的其他尺寸
Apertus 70B — 常见问题
How much VRAM does Apertus 70B need?
About 43 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 Apertus 70B run on an RTX 4090 (24 GB)?
No. Apertus 70B needs about 43 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 Apertus 70B locally?
Install Ollama and run `ollama run apertus`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Apertus come in?
Apertus 8B (6 GB), Apertus 70B (43 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.