GLM-5.2 744B — 显存、速度与本地部署
作者： Jakub Rusinowski · 最后更新：
The full GLM-5.2 MoE. At 744B total parameters this needs roughly 400 GB even at Q4 — a multi-node or datacenter deployment, not a workstation, despite the modest ~40B active count. Reach it through the Z.ai API or a hosted provider unless you have that hardware. The 1M-token context and MIT license are what set it apart from other models at this scale.
GLM-5.2 744B 在 Q4_K_M 下约需 450 GB 显存——量化权重加框架开销，不含 KV 缓存。在 Apple Silicon 上，这部分来自统一内存。
按量化级别的显存与速度
计算基准：NVIDIA RTX 4090 (24 GB)。仅含权重与开销：该模型架构未公开，因此未计入 KV 缓存。
| 量化 | 显存 | 显存 | 速度（估算） | 适配 |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 245.4 GB | — | 放不下 | |
| Q3_K_M 3.41 bpw | 317.9 GB | — | 放不下 | |
| Q4_K_M 4.83 bpw | 450 GB | — | 放不下 | |
| Q5_K_M 5.67 bpw | 528.1 GB | — | 放不下 | |
| Q6_K 6.56 bpw | 610.9 GB | — | 放不下 | |
| Q8_0 8.50 bpw | 791.3 GB | — | 放不下 | |
| F16 16.00 bpw | 1488.8 GB | — | 放不下 |
黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型，详见 方法说明页. GLM-5.2 744B 显存计算器 →
运行 GLM-5.2 744B
目录中能运行 GLM-5.2 744B 的最便宜 GPU 是 Apple M3 Ultra (512 GB).
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
如何运行 GLM-5.2 744B
安装 Ollama，然后运行：
ollama run glm-5-2规格
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
Preview — The model is released, but these specs are thin or rest on a single source. Individual fields may be wrong.
- 参数量
- 744 Billion (~40B active)
- 上下文窗口
- 1,000,000
- 架构
- Mixture-of-Experts (two reasoning-effort levels)
- 提供商
- Zhipu AI (Z.ai)
- 许可证
- MIT
- 规格量化
- Q4_K_M
- 系统内存
- 768 GB
- 记录更新于
- 2026-08-15
Commercial use permitted. No usage restrictions beyond attribution.
质量与使用场景
评分由模型作者或独立评测方发布——衡量质量而非吞吐量，并非我们实测。
我的 GPU 能运行 GLM-5.2 744B 吗？
GLM-5.2 744B — 常见问题
How much VRAM does GLM-5.2 744B need?
About 450 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does GLM-5.2 744B run on an RTX 4090 (24 GB)?
No. GLM-5.2 744B needs about 450 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run GLM-5.2 744B locally?
Install Ollama and run `ollama run glm-5-2`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.