# Can I run Sarvam-30B on Apple M3 Ultra (256GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~21.7 GB of ~192 GB usable. You have room for FP16 for higher quality.

- Model: 30B (MoE, 2.4B active), Q4_K_M 19.6 GB
- Device: 256 GB unified, ~192 GB usable for weights
- Needs ~21.7 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on macOS: LM Studio

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://huggingface.co/sarvamai/sarvam-30b, https://huggingface.co/sarvamai/sarvam-30b-gguf, https://www.sarvam.ai/blogs/sarvam-30b-105b.

More: https://localmodel.run/can-i-run/sarvam-30b/apple-m3-ultra-256gb