Solar Open — Upstage 的本地 AI 模型
作者: Jakub Rusinowski · 最后更新:
Upstage 的开放权重 Solar 模型。Solar Open 2 是总参数 250B、每个 token 激活 15B 的混合专家模型,其混合注意力只让四分之一的层保留 KV 缓存,从而支持 1M token 上下文。采用 Upstage Solar 许可:Apache-2.0 条款,外加衍生模型须以“Solar”命名的义务。
变体
Solar Open 最小的变体在 Q4_K_M 下约需 152 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 |
|---|---|---|---|---|
| Solar Open 2 250B-A15B → 250B (15B active) | ~151.9 GB | 1,048,576 | ollama run solar-open |
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 Solar Open
安装 Ollama,然后拉取标签。
ollama run solar-open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: Solar Open 2 250B-A15B推荐 GPU
目录中能在本地运行 Solar Open(至少 152 GB 显存)的最便宜 GPU 是 Apple M3 Ultra (512 GB).
Solar Open — 常见问题
How much VRAM does Solar Open need?
Solar Open needs about 152 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Solar Open 2 250B-A15B (152 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Solar Open on an RTX 4090 (24 GB)?
Solar Open's smallest variant needs about 152 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for Solar Open?
Q4_K_M is the best balance of quality and VRAM for Solar Open 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 Solar Open with Ollama?
Solar Open has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.