AutoJev — denis-pplx 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
基于 Qwen3.8-27B 的 27B 多模态决策模型，截至 2026 年 9 月 28 日是社区 Decision Index 上得分最高的可下载模型。
变体
AutoJev 最小的变体在 Q4_K_M 下约需 18 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 |
|---|---|---|---|---|
| AutoJev 27B → 27B | ~17.6 GB | Not published | autojev-serve :8000 |
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 AutoJev
安装 Ollama，然后拉取标签。
Served by autojev-serve (default port 8000). 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: AutoJev 27B推荐 GPU
目录中能在本地运行 AutoJev（至少 18 GB 显存）的最便宜 GPU 是 AMD Radeon RX 7900 XT (20 GB).
AutoJev — 常见问题
How much VRAM does AutoJev need?
AutoJev needs about 18 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: AutoJev 27B (18 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run AutoJev on an RTX 4090 (24 GB)?
Yes — AutoJev 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 AutoJev?
Q4_K_M is the best balance of quality and VRAM for AutoJev 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 AutoJev locally?
AutoJev 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.