EuroLLM — Unbabel / Instituto Superior Técnico / INESC-ID 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
在巴塞罗那超级计算中心的MareNostrum 5超级计算机上从零训练，覆盖欧盟全部24种官方语言。这是欧洲对多语言支持只是附带功能的那类模型给出的回应：欧盟语言是训练目标，而不是副产品。
变体
EuroLLM 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 |
|---|---|---|---|---|
| EuroLLM 9B → 9B | ~6.2 GB | 4,096 | ollama run eurollm | |
| EuroLLM 22B → 22B | ~14.1 GB | 4,096 | ollama run eurollm |
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 EuroLLM
安装 Ollama，然后拉取标签。
ollama run eurollm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: EuroLLM 9B, EuroLLM 22B推荐 GPU
目录中能在本地运行 EuroLLM（至少 6 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
EuroLLM — 常见问题
How much VRAM does EuroLLM need?
EuroLLM needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: EuroLLM 9B (6 GB, Q4_K_M); EuroLLM 22B (14 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run EuroLLM on an RTX 4090 (24 GB)?
Yes — EuroLLM 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 EuroLLM?
Q4_K_M is the best balance of quality and VRAM for EuroLLM 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 EuroLLM with Ollama?
EuroLLM 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.