# Can I run Mistral Small 3 24B on Apple M4 (16GB)?

Updated: 2026-06-15

**No, not enough memory.** Needs ~16.3 GB even at Q4_K_M, but only ~10.5 GB is usable.

- Model: 24B, Q4_K_M 14.33 GB
- Device: 16 GB unified, ~10.5 GB usable for weights
- Needs ~16.3 GB at Q4_K_M; recommended quant: n/a
- Best tool on macOS: LM Studio
- Command: `ollama run mistral-small3.2:24b`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/mistral-small3.2, https://ollama.com/library/mistral-small3.2/tags, https://huggingface.co/bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF, https://docs.mistral.ai/models/model-cards/mistral-small-3-2-25-06, https://lmarena.ai/leaderboard.

More: https://localmodel.run/can-i-run/mistral-small-3-24b/apple-m4-16gb