# Can I run Sarvam-M 24B on iPhone 16 Pro?

> **No, not enough memory.** Needs ~16.3 GB even at Q4_K_M, but only ~4.5 GB is usable.

Last validated: 2026-06-15.

## Memory math
- Sarvam-M 24B: 24B; Q4_K_M weighs 14.3 GB on disk.
- At Q4_K_M with a 4k context it needs ~16.3 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- iPhone 16 Pro: 8 GB unified, ~4.5 GB usable for model weights.
- Headroom: ~-11.8 GB.

## How to run
Recommended quant: n/a. Best tool on iOS: Apple Foundation Models.

## Run Sarvam-M 24B on other devices
- [Nvidia GeForce RTX 4090 (24GB)](https://localmodel.run/can-i-run/sarvam-m-24b/nvidia-rtx-4090-24gb)
- [Nvidia GeForce RTX 3090 (24GB)](https://localmodel.run/can-i-run/sarvam-m-24b/nvidia-rtx-3090-24gb)
- [AMD Radeon RX 7900 XTX (24GB)](https://localmodel.run/can-i-run/sarvam-m-24b/amd-rx-7900-xtx-24gb)
- [Nvidia GeForce RTX 5090 (32GB)](https://localmodel.run/can-i-run/sarvam-m-24b/nvidia-rtx-5090-32gb)
- [32GB RAM Laptop (CPU/iGPU only)](https://localmodel.run/can-i-run/sarvam-m-24b/laptop-32gb)
- [Apple M5 (32GB)](https://localmodel.run/can-i-run/sarvam-m-24b/apple-m5-32gb)

## Other models that run on iPhone 16 Pro
- [Gemma 3 4B (4B)](https://localmodel.run/can-i-run/gemma-3-4b/iphone-16-pro)
- [Qwen3 4B (4B)](https://localmodel.run/can-i-run/qwen3-4b/iphone-16-pro)
- [Phi-3.5-mini 3.8B (3.82B)](https://localmodel.run/can-i-run/phi-3.5-mini/iphone-16-pro)
- [Phi-4-mini 3.8B (3.8B)](https://localmodel.run/can-i-run/phi-4-mini-3.8b/iphone-16-pro)
- [Qwen2.5-VL 3B (3.75B)](https://localmodel.run/can-i-run/qwen2.5-vl-3b/iphone-16-pro)
- [Qwen2.5 3B (3.09B)](https://localmodel.run/can-i-run/qwen2.5-3b/iphone-16-pro)

Estimate, not a guarantee. 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/iphone-16-pro