d1 — Liquid AI 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Liquid AI 面向边缘设备的决策模型：d1-3B（文本与图像，基于 LFM2.5-VL-3B）和实验性的 d1-omni-600M（文本加图像或音频）。通过 Transformers 加载的 Python 库，而非服务器；采用 LFM Open License v1.0 许可。
变体
d1 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 |
|---|---|---|---|---|
| d1-3B → 3B | ~2.7 GB | 32K (32,768) | Transformers (trust_remote_code) | |
| d1-omni-600M → 600M | ~1.2 GB | 16K (16,384; 896 text tokens with images) | Transformers (trust_remote_code) |
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 d1
安装 Ollama，然后拉取标签。
A Python library: you load it inside your own program. It has no HTTP server and 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
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
适用于: d1-3B, d1-omni-600M推荐 GPU
目录中能在本地运行 d1（至少 1 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
d1 — 常见问题
How much VRAM does d1 need?
d1 needs about 1 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: d1-3B (3 GB, Q4_K_M); d1-omni-600M (1 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run d1 on an RTX 4090 (24 GB)?
Yes — d1 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 d1?
Q4_K_M is the best balance of quality and VRAM for d1 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 d1 locally?
d1 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.