Nimble — Bespoke Labs 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Bespoke Labs 的 9B 决策模型，基于 Qwen3.5-9B 的 LoRA，使用对比数据对训练。是 Ollama 库中的默认决策模型。
变体
Nimble 最小的变体在 Q4_K_M 下约需 7 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 |
|---|---|---|---|---|
| Nimble 9B → 9B | ~6.6 GB | 8K (prompt limit) | ollama pull nimble |
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 Nimble
安装 Ollama，然后拉取标签。
ollama pull nimble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: Nimble 9B推荐 GPU
目录中能在本地运行 Nimble（至少 7 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
Nimble — 常见问题
How much VRAM does Nimble need?
Nimble needs about 7 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Nimble 9B (7 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Nimble on an RTX 4090 (24 GB)?
Yes — Nimble 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 Nimble?
Q4_K_M is the best balance of quality and VRAM for Nimble 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 Nimble locally?
Nimble is a decision model: it is called over an HTTP endpoint (/v1/systemone), not chatted with. Where a variant is available in Ollama 0.35 or newer, pull it with `ollama pull` and send requests to the local server; the others ship their own server. Each variant page shows the exact commands for that model.