# Can I run GLM-4 9B on Apple M4 Max (128GB)?

> **Yes, it runs.** Runs at Q4_K_M using ~7.3 GB of ~96 GB usable. You have room for FP16 for higher quality.

Last validated: 2026-06-15.

## Memory math
- GLM-4 9B: 9B; Q4_K_M weighs 5.82 GB on disk.
- At Q4_K_M with a 4k context it needs ~7.3 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- Apple M4 Max (128GB): 128 GB unified, ~96 GB usable for model weights.
- Headroom: ~88.7 GB; it also fits FP16 for higher quality.

## How to run
Recommended quant: Q4_K_M. Best tool on macOS: LM Studio.

```sh
ollama run glm4:9b
```

## Run GLM-4 9B on other devices
- [Nvidia GeForce RTX 3060 (12GB)](https://localmodel.run/can-i-run/glm-4-9b/nvidia-rtx-3060-12gb)
- [Nvidia GeForce RTX 4070 (12GB)](https://localmodel.run/can-i-run/glm-4-9b/nvidia-rtx-4070-12gb)
- [Samsung Galaxy S24 Ultra](https://localmodel.run/can-i-run/glm-4-9b/samsung-s24-ultra)
- [Generic Android Phone (12GB RAM)](https://localmodel.run/can-i-run/glm-4-9b/android-generic-12gb)
- [iPhone 17 Pro](https://localmodel.run/can-i-run/glm-4-9b/iphone-17-pro)
- [iPhone Air](https://localmodel.run/can-i-run/glm-4-9b/iphone-air)

## Other models that run on Apple M4 Max (128GB)
- [gpt-oss 120B (117B)](https://localmodel.run/can-i-run/gpt-oss-120b/apple-m4-max-128gb)
- [Llama 4 Scout (109B)](https://localmodel.run/can-i-run/llama-4-scout/apple-m4-max-128gb)
- [Sarvam-105B (105B)](https://localmodel.run/can-i-run/sarvam-105b/apple-m4-max-128gb)
- [Qwen2.5 72B (72B)](https://localmodel.run/can-i-run/qwen2.5-72b/apple-m4-max-128gb)
- [Llama 3.3 70B (70B)](https://localmodel.run/can-i-run/llama-3.3-70b/apple-m4-max-128gb)
- [Mixtral 8x7B (46.7B)](https://localmodel.run/can-i-run/mixtral-8x7b/apple-m4-max-128gb)

Estimate, not a guarantee. Sources: https://ollama.com/library/glm4, https://ollama.com/library/glm4/tags, https://huggingface.co/bartowski/glm-4-9b-chat-GGUF, https://huggingface.co/THUDM/glm-4-9b-chat.
More: https://localmodel.run/can-i-run/glm-4-9b/apple-m4-max-128gb