# Can I run Sarvam-M 24B on Apple M3 Pro (18GB)?

Updated: 2026-06-15

**No, not enough memory.** Needs ~16.3 GB even at Q4_K_M, but only ~12 GB is usable.

- Model: 24B, Q4_K_M 14.3 GB
- Device: 18 GB unified, ~12 GB usable for weights
- Needs ~16.3 GB at Q4_K_M; recommended quant: n/a
- Best tool on macOS: LM Studio

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://huggingface.co/sarvamai/sarvam-m, https://huggingface.co/lmstudio-community/sarvam-m-GGUF, https://huggingface.co/sarvamai/sarvam-m-q8-gguf.

More: https://localmodel.run/can-i-run/sarvam-m-24b/apple-m3-18gb