Local AI hardware guide

What machines can deploy Google Gemma locally?

Updated July 28, 2026 · HiRAM Deals

A 32 GB computer is the practical starting point for experimenting with current quantized Gemma models and large contexts. Move to 64 GB or more when you want larger models, more context headroom, or several workloads at once.

The short answer: choose 32 GB RAM for smaller quantized models, 64 GB for a comfortable workstation, and 96–128 GB when you want larger models or less compromise. A supported discrete GPU improves speed, but CPU-only inference is possible.

Which Gemma should you run?

Google’s current Gemma 4 family includes smaller edge models plus 12B, 26B mixture-of-experts, and 31B workstation models. Google lists 128K context for the smaller models and 256K for medium models. Ollama packages current quantized variants from roughly 7 GB to 20 GB before context and application overhead.

32 GB RAM

Good entry point for Gemma 4 E2B, E4B, and 12B quantized builds. It leaves useful room beyond model weights, but very long prompts can still exhaust memory.

64 GB RAM

Our general recommendation for a smooth local workstation: larger context caches, the 26B or 31B quantized models, and room for development tools.

96–128 GB RAM

Best for long-context work, multiple models, CPU-heavy inference, or avoiding aggressive quantization. More RAM is capacity—not a substitute for GPU bandwidth.

About the 100K-token target

Thirty-two gigabytes is a sensible minimum for trying a 100K-token context with a smaller quantized model, but it is not a universal guarantee. The model weights are only one part of memory use. The KV cache grows with model size and token count, while Ollama, the operating system, image inputs, and other applications need memory too. For dependable 100K-token use, prefer 64 GB and verify the exact model, quantization, and runtime configuration.

Install with Ollama

Ollama is the simplest cross-platform starting point. After installing it, run:

ollama run gemma4

Choose an explicit tag when you need predictable model size. See the Gemma 4 model library on Ollama.

What matters when buying a machine

Installed RAM: 32 GB minimum; 64 GB recommended for sustained local-AI work.
GPU memory: enough VRAM can keep more of the model on the GPU and materially improve speed.
Memory bandwidth: CPU-only generation often becomes bandwidth-bound.
Upgrade capacity: used workstations with spare DIMM slots can be better values than sealed consumer systems.
Storage: leave space for several multi-gigabyte model files.