Decider — Mapika 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
基于 Qwen3.5 基座（0.8B 至 35B-A3B）的开源决策模型系列，接口统一，每个问题最多支持 255 个选项，并配有兼容 TypeSafe 的服务器。
变体
Decider 最小的变体在 Q4_K_M 下约需 1 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 |
|---|---|---|---|---|
| Decider 0.8B 0.8B | ~1.3 GB | Not published | decider.serve | |
| Decider 2B → 2B | ~2.2 GB | 32K | decider.serve | |
| Decider 4B → 4B | ~3.6 GB | Not published | decider.serve | |
| Decider 35B-A3B (NVFP4) → 35B (3B active) | ~22.5 GB | Not published | decider.serve |
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 Decider
安装 Ollama，然后拉取标签。
Served by decider.serve. This model does not run in Ollama.
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: Decider 0.8B, Decider 2B, Decider 4B, Decider 35B-A3B (NVFP4)推荐 GPU
目录中能在本地运行 Decider（至少 1 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
Decider — 常见问题
How much VRAM does Decider need?
Decider needs about 1 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Decider 0.8B (1 GB, Q4_K_M); Decider 2B (2 GB, Q4_K_M); Decider 4B (4 GB, Q4_K_M); Decider 35B-A3B (NVFP4) (23 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Decider on an RTX 4090 (24 GB)?
Yes — Decider 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 Decider?
Q4_K_M is the best balance of quality and VRAM for Decider 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 Decider locally?
Decider 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.