# Can I run Sarvam-30B on 16GB RAM Laptop (CPU/iGPU only)?

> **No, not enough memory.** Needs ~21.7 GB even at Q4_K_M, but only ~12 GB is usable.

Last validated: 2026-06-15.

## Memory math
- Sarvam-30B: 30B (MoE, 2.4B active); Q4_K_M weighs 19.6 GB on disk.
- At Q4_K_M with a 4k context it needs ~21.7 GB (weights + KV cache + ~0.8 GB runtime overhead, ±15% with context length).
- 16GB RAM Laptop (CPU/iGPU only): 16 GB ram, ~12 GB usable for model weights.
- Headroom: ~-9.7 GB.

## How to run
Recommended quant: n/a. Best tool on Windows: LM Studio.

## Run Sarvam-30B on other devices
- [Nvidia GeForce RTX 4090 (24GB)](https://localmodel.run/can-i-run/sarvam-30b/nvidia-rtx-4090-24gb)
- [Nvidia GeForce RTX 3090 (24GB)](https://localmodel.run/can-i-run/sarvam-30b/nvidia-rtx-3090-24gb)
- [AMD Radeon RX 7900 XTX (24GB)](https://localmodel.run/can-i-run/sarvam-30b/amd-rx-7900-xtx-24gb)
- [Nvidia GeForce RTX 5090 (32GB)](https://localmodel.run/can-i-run/sarvam-30b/nvidia-rtx-5090-32gb)
- [32GB RAM Laptop (CPU/iGPU only)](https://localmodel.run/can-i-run/sarvam-30b/laptop-32gb)
- [Apple M4 Pro (48GB)](https://localmodel.run/can-i-run/sarvam-30b/apple-m4-pro-48gb)

## Other models that run on 16GB RAM Laptop (CPU/iGPU only)
- [Phi-4 14B (14B)](https://localmodel.run/can-i-run/phi-4-14b/laptop-16gb)
- [Qwen2.5 14B (14B)](https://localmodel.run/can-i-run/qwen2.5-14b/laptop-16gb)
- [Qwen3 14B (14B)](https://localmodel.run/can-i-run/qwen3-14b/laptop-16gb)
- [DeepSeek-R1-Distill-Qwen 14B (14B)](https://localmodel.run/can-i-run/deepseek-r1-distill-qwen-14b/laptop-16gb)
- [Qwen2.5 Coder 14B (14B)](https://localmodel.run/can-i-run/qwen2.5-coder-14b/laptop-16gb)
- [Mistral Nemo 12B (12.2B)](https://localmodel.run/can-i-run/mistral-nemo-12b/laptop-16gb)

Estimate, not a guarantee. 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/laptop-16gb