WisePC

Workload guide · AI

Code assistant (local LLM): hardware requirements guide

Local code completion and chat models (Ollama, Continue).

Hardware requirements by tier

Three tiers for every workload: the minimum that works, the recommended sweet spot, and the comfortable headroom level. These are the same tiers the WisePC decision engine uses when it plans a build around your goal.

TierCPU coresRAMStorageGPUNetwork
Minimum8 cores16 GB1 TB (ssd)ai1 GbE
Recommended12 cores32 GB1 TB (ssd)ai2.5 GbE
Comfortable16 cores64 GB2 TB (ssd)ai2.5 GbE

Which tier do you need?

Frequently asked questions

How much RAM does code assistant (local llm) need?

16 GB is the sensible minimum, 32 GB covers most real setups, and 64 GB gives comfortable headroom for growth and extra services.

How many CPU cores does code assistant (local llm) need?

A 8-core CPU is the minimum, 12 cores is the recommended sweet spot, and 16 cores is comfortable when it shares the machine with other workloads.

Does code assistant (local llm) need a dedicated GPU?

A dedicated GPU is strongly recommended — this workload does AI compute.

What storage and network does code assistant (local llm) expect?

Storage: 1 TB of SSD is the recommended baseline (1 TB minimum, 2 TB comfortable). Network: 2.5 GbE is the recommended baseline.

What runs well alongside code assistant (local llm)?

It pairs naturally with: Local AI inference, Dev environments.

Plan your own

Related workload guides