Kimi K2.5 / K2.6 / K2.7 — Moonshot AI 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Moonshot AI 2026年2月的突破之作。Kimi K2.5拥有1万亿总参数（32B活跃，384专家），创下HumanEval历史最高分99.0。在15万亿混合视觉和文本token上训练。具备独特的智能体群集架构。
变体
Kimi K2.5 / K2.6 / K2.7 最小的变体在 Q4_K_M 下约需 605 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 |
|---|---|---|---|---|
| Kimi K2.5 → 1T/32B active | ~604.6 GB | 256,000 | ollama run hf.co/moonshotai/Kimi-K2.5-Instruct-Q4_K_M | |
| Kimi K2.6 → 1T/32B active | ~604.6 GB | 256,000 | ollama run hf.co/moonshotai/Kimi-K2.6-Instruct-Q4_K_M | |
| Kimi K2.5 1T (32B Active) 1T/32B active | ~604.6 GB | 256,000 | ollama run hf.co/moonshotai/Kimi-K2.5 | |
| Kimi K2.7 Code → 1T/32B active | ~604.6 GB | 262,144 | ollama run kimi-k2 |
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 Kimi K2.5 / K2.6 / K2.7
安装 Ollama，然后拉取标签。
ollama run hf.co/moonshotai/Kimi-K2.5-Instruct-Q4_K_M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: Kimi K2.5, Kimi K2.6, Kimi K2.7 CodeWeights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
适用于: Kimi K2.5 1T (32B Active)Kimi K2.5 / K2.6 / K2.7 — 常见问题
How much VRAM does Kimi K2.5 / K2.6 / K2.7 need?
Kimi K2.5 / K2.6 / K2.7 needs about 605 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Kimi K2.5 (605 GB, Q4_K_M); Kimi K2.6 (605 GB, Q4_K_M); Kimi K2.5 1T (32B Active) (605 GB, Q4_K_M); Kimi K2.7 Code (605 GB, INT4 (native)). On Apple Silicon, unified memory counts toward this requirement.
Can I run Kimi K2.5 / K2.6 / K2.7 on an RTX 4090 (24 GB)?
Kimi K2.5 / K2.6 / K2.7's smallest variant needs about 605 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 Kimi K2.5 / K2.6 / K2.7?
Q4_K_M is the best balance of quality and VRAM for Kimi K2.5 / K2.6 / K2.7 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 Kimi K2.5 / K2.6 / K2.7 with Ollama?
Install Ollama, then run: ollama run hf.co/moonshotai/Kimi-K2.5-Instruct-Q4_K_M. This downloads Kimi K2.5 / K2.6 / K2.7 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.