Skip to content
localmodel.run

text model · Sarvam · Windows

S Can I run Sarvam-30B on 8GB RAM Laptop (CPU/iGPU only)?

Compatibility verdict VRAM threshold engine
No, not enough memorywould not load

No. Sarvam-30B needs ~21.7 GB even at Q4_K_M, but 8GB RAM Laptop (CPU/iGPU only) only has ~5 GB usable.

Needs ~21.7 GB Device usable ~5 GB

Needs ~21.7 GB even at Q4_K_M, but only ~5 GB is usable.

Q4_K_M needed
~21.7 GB
Usable on device
~5 GB
Device memory
8 GB

How to run it

On Windows use LM Studio (Best GUI on Windows, auto-detects CUDA/Vulkan backends.). AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Model Sarvam
Parameters
30B (MoE, 2.4B active)
Q4_K_M size
19.6 GB
Context
64k
Full Sarvam-30B requirements →
Device Windows
Memory
8 GB ram
Usable for weights
~5 GB
Best runtime
Ollama (llama.cpp backend)
Best models for 8GB RAM Laptop (CPU/iGPU only) →

What you can run instead

Run Sarvam-30B on other hardware

FAQ

Can 8GB RAM Laptop (CPU/iGPU only) run Sarvam-30B?

No. Sarvam-30B needs ~21.7 GB even at Q4_K_M, but 8GB RAM Laptop (CPU/iGPU only) only has ~5 GB usable.

How much memory does Sarvam-30B need?

8GB RAM Laptop (CPU/iGPU only) 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 Windows?

LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.

Sources

Memory figures are estimates. See methodology.