MiMo-V2.5 — Xiaomi 的本地 AI 模型

作者： Jakub Rusinowski · 最后更新： 2026年9月6日

已被取代的模型. MiMo-V2.5 已被 MiMo-V2.6 取代。本页仅作参考保留；更新的系列是更好的起点。查看 MiMo-V2.6 →

Xiaomi's MIT-licensed MoE pair, and the clearest licence story at the trillion-parameter tier — MIT, not a bespoke open-weight agreement with revenue thresholds. Both carry 1M-token context and agentic multimodal capability. Consistently omitted from best-of roundups despite matching Kimi K2.6 on aggregate index scores.

Xiaomi MiMo Hugging Face

变体

MiMo-V2.5 最小的变体在 Q4_K_M 下约需 188 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
MiMo-V2.5 310B → 310B/15B active		~188 GB	1,000,000	`ollama run mimo-v2-5`
MiMo-V2.5-Pro 1T → 1T/42B active		~604.6 GB	1,000,000	`ollama run mimo-v2-5`

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 MiMo-V2.5

安装 Ollama，然后拉取标签。

$ollama run mimo-v2-5

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

MIT允许商业使用

Commercial use permitted. No usage restrictions beyond attribution.

适用于: MiMo-V2.5 310B, MiMo-V2.5-Pro 1T

我的 GPU 能运行 MiMo-V2.5 吗？

MiMo-V2.5 — 常见问题

How much VRAM does MiMo-V2.5 need?

MiMo-V2.5 needs about 188 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: MiMo-V2.5 310B (188 GB, Q4_K_M); MiMo-V2.5-Pro 1T (605 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run MiMo-V2.5 on an RTX 4090 (24 GB)?

MiMo-V2.5's smallest variant needs about 188 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 MiMo-V2.5?

Q4_K_M is the best balance of quality and VRAM for MiMo-V2.5 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 MiMo-V2.5 with Ollama?

MiMo-V2.5 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.

官方链接