GLM-4.6V — Zhipu AI (Z.ai) 的本地 AI 模型
作者： Jakub Rusinowski · 最后更新：
Z.ai的视觉语言产品线。Flash成员是9B的高效变体，以极小的算力代价共享GLM-4.6V的多模态能力，小到可以装进8 GB显卡。
变体
GLM-4.6V 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 |
|---|---|---|---|---|
| GLM-4.6V-Flash 9B → 9B | ~6.2 GB | 65,536 | ollama run glm-4-6v |
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 GLM-4.6V
安装 Ollama，然后拉取标签。
ollama run glm-4-6v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: GLM-4.6V-Flash 9B推荐 GPU
目录中能在本地运行 GLM-4.6V（至少 6 GB 显存）的最便宜 GPU 是 Intel Arc B570 (10 GB).
GLM-4.6V — 常见问题
How much VRAM does GLM-4.6V need?
GLM-4.6V needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: GLM-4.6V-Flash 9B (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run GLM-4.6V on an RTX 4090 (24 GB)?
Yes — GLM-4.6V 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 GLM-4.6V?
Q4_K_M is the best balance of quality and VRAM for GLM-4.6V 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 GLM-4.6V with Ollama?
GLM-4.6V 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.