# Can I run Llama 3.3 70B on Apple M4 Max (128GB)?

> **Yes, it runs.** Runs at Q4_K_M using ~45.3 GB of ~96 GB usable. You have room for Q8_0 for higher quality.

Last validated: 2026-06-15.

## Memory math
- Llama 3.3 70B: 70B; Q4_K_M weighs 42.52 GB on disk.
- At Q4_K_M with a 4k context it needs ~45.3 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: ~50.7 GB; it also fits Q8_0 for higher quality.

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

```sh
ollama run llama3.3:70b
```

## Run Llama 3.3 70B on other devices
- [Apple M4 Max (64GB)](https://localmodel.run/can-i-run/llama-3.3-70b/apple-m4-max-64gb)
- [Apple M5 Max (128GB)](https://localmodel.run/can-i-run/llama-3.3-70b/apple-m5-max-128gb)
- [Apple M3 Ultra (256GB)](https://localmodel.run/can-i-run/llama-3.3-70b/apple-m3-ultra-256gb)

## 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)
- [Mixtral 8x7B (46.7B)](https://localmodel.run/can-i-run/mixtral-8x7b/apple-m4-max-128gb)
- [Command R 35B (35B)](https://localmodel.run/can-i-run/command-r-35b/apple-m4-max-128gb)

Estimate, not a guarantee. Sources: https://ollama.com/library/llama3.3, https://ollama.com/library/llama3.3/tags, https://huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF, https://lmarena.ai/leaderboard.
More: https://localmodel.run/can-i-run/llama-3.3-70b/apple-m4-max-128gb