Winnow — EldanRing 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
基于 Gemma 4 微调的类型化决策模型，以 GGUF 发布，配套基于 llama.cpp 的服务器，同一个已加载的模型同时提供 /v1/systemone 与聊天、视觉能力。
变体
Winnow 最小的变体在 Q4_K_M 下约需 6 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 |
|---|---|---|---|---|
| Winnow 12B → 12B | ~8 GB | Not published | winnow-inference :8091 | |
| Winnow E4B → E4B (8B total) | ~5.6 GB | Not published | winnow-inference :8091 |
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 Winnow
安装 Ollama，然后拉取标签。
Served by winnow-inference (default port 8091). 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: Winnow 12B, Winnow E4B推荐 GPU
目录中能在本地运行 Winnow（至少 6 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
Winnow — 常见问题
How much VRAM does Winnow need?
Winnow needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Winnow 12B (8 GB, Q4_K_M); Winnow E4B (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Winnow on an RTX 4090 (24 GB)?
Yes — Winnow 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 Winnow?
Q4_K_M is the best balance of quality and VRAM for Winnow 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 Winnow locally?
Winnow 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.