text model · Sarvam · macOS
S Can I run Sarvam-30B on Apple M3 Pro (18GB)?
No. Sarvam-30B needs ~21.7 GB even at Q4_K_M, but Apple M3 Pro (18GB) only has ~12 GB usable.
Needs ~21.7 GB even at Q4_K_M, but only ~12 GB is usable.
- Q4_K_M needed
- ~21.7 GB
- Usable on device
- ~12 GB
- Device memory
- 18 GB
How to run it
On macOS use LM Studio (Polished GUI, ships MLX on Apple Silicon, one-click model downloads.). vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
- Parameters
- 30B (MoE, 2.4B active)
- Q4_K_M size
- 19.6 GB
- Context
- 64k
- Memory
- 18 GB unified
- Usable for weights
- ~12 GB
- Best runtime
- Ollama (llama.cpp Metal backend) / MLX
What you can run instead
Run Sarvam-30B on other hardware
FAQ
Can Apple M3 Pro (18GB) run Sarvam-30B?
No. Sarvam-30B needs ~21.7 GB even at Q4_K_M, but Apple M3 Pro (18GB) only has ~12 GB usable.
How much memory does Sarvam-30B need?
Apple M3 Pro (18GB) does not have enough memory. At Q4_K_M the weights are ~19.6 GB; with KV cache and runtime overhead, budget ~21.7 GB at a 4k context. It is a Mixture-of-Experts model (30B total / 2.4B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Sarvam-30B on macOS?
LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
Sources
Memory figures are estimates. See methodology.