Zhipu AI · chatglm
Can I run glm4?
A strong multi-lingual general language model with competitive performance to Llama 3.
9.4B parameters128K contexttextThe glm-4-9b License12 builds
glm4 system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| glm4:9b-text-q4_0 | Q4_0 | 5.1 GB | ~7.7 GB(est.) |
| glm4:9b | Q4_0 | 5.1 GB | ~7.7 GB(est.) |
| glm4:9b-text-q4_K_M | Q4_K_M | 5.8 GB | ~8.7 GB(est.) |
| glm4:9b-chat-q4_K_M | Q4_K_M | 5.8 GB | ~8.7 GB(est.) |
| glm4:9b-text-q5_K_M | Q5_K_M | 6.7 GB | ~9.9 GB(est.) |
| glm4:9b-chat-q5_K_M | Q5_K_M | 6.7 GB | ~9.9 GB(est.) |
| glm4:9b-text-q6_K | Q6_K | 7.7 GB | ~11.4 GB(est.) |
| glm4:9b-chat-q6_K | Q6_K | 7.7 GB | ~11.4 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run glm4 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run glm4:9b-text-q4_0 - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about glm4
- How much VRAM do I need to run glm4?
- At 4K context, the smallest published build of glm4 (Q4_0) needs roughly 7.7 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run glm4 without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 7.7 GB of free RAM for the smallest build.
- How big is the glm4 download?
- The smallest published build is 5.1 GB. There are 12 builds in total, the largest being 17.5 GB. Leave some extra free disk space beyond the download itself.
- How do I run glm4 locally?
- Install Ollama, then run "ollama run glm4:9b-text-q4_0" in a terminal. The weights download on first use and an interactive session opens.
Will glm4 run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026