Mellum2.1 — JetBrains 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
JetBrains 的开放编程模型。Mellum2.1 Thinking 是 12B 参数、2.5B 激活的混合专家模型，主要通过在真实代码仓库中的强化学习进行后训练（使用 shell 和文件编辑工具，测试通过即获得奖励），用于智能体式软件工程和作为子智能体。Apache 2.0，上下文 131,072 token。Q4_K_M 约 8 GB，是少数能装进中端笔记本的智能体编程模型之一。
变体
Mellum2.1 最小的变体在 Q4_K_M 下约需 9 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 |
|---|---|---|---|---|
| Mellum2.1 12B Thinking → 12B (2.5B active) | ~8.9 GB | 131,072 | 云端托管标签 |
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 Mellum2.1
安装 Ollama，然后拉取标签。
No Ollama library entry yet. JetBrains' official GGUF files are the local route; the card's own serving recipe is vLLM.
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: Mellum2.1 12B Thinking推荐 GPU
目录中能在本地运行 Mellum2.1（至少 9 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
Mellum2.1 — 常见问题
How much VRAM does Mellum2.1 need?
Mellum2.1 needs about 9 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Mellum2.1 12B Thinking (9 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Mellum2.1 on an RTX 4090 (24 GB)?
Yes — Mellum2.1 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 Mellum2.1?
Q4_K_M is the best balance of quality and VRAM for Mellum2.1 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 Mellum2.1 with Ollama?
Mellum2.1 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.