Shieldstral — Mistral AI 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Mistral 的开放权重内容审核分类器，支持文本和图像。你在每个请求中以是/否问题的形式给出策略，它返回经过校准的安全分数，因此一个模型无需重新训练即可服务多种策略。Apache-2.0。
变体
Shieldstral 最小的变体在 Q4_K_M 下约需 3 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 |
|---|---|---|---|---|
| Shieldstral 1.0 3B → 3.8B | ~3.1 GB | 32,768 | 云端托管标签 |
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 Shieldstral
安装 Ollama，然后拉取标签。
No Ollama tag. Mistral documents vLLM and llama.cpp builds on the model card.
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
Commercial use permitted. No usage restrictions beyond attribution.
适用于: Shieldstral 1.0 3B推荐 GPU
目录中能在本地运行 Shieldstral（至少 3 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
Shieldstral — 常见问题
How much VRAM does Shieldstral need?
Shieldstral needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Shieldstral 1.0 3B (3 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Shieldstral on an RTX 4090 (24 GB)?
Yes — Shieldstral runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for Shieldstral?
Q4_K_M is the best balance of quality and VRAM for Shieldstral 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 Shieldstral with Ollama?
Shieldstral has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.