Full directory
GUIDE BY CAPACITY

With 12–16 GB,
here is what really runs.

Experiences reported by people using their machines every day. Not a performance promise: a concrete place to start.

6documented uses
in this range
Documents

A fully local OCR and RAG pipeline for a self-hosted document server

Rather than one big general model, this setup uses several small, fast ones for narrowly scoped, deterministic jobs — starting with OCR and metadata for a self-hosted Paperless document server.

Personal assistant

An agent that plans a wedding from your inbox

The same low-key homelab setup also runs a semi-agentic wedding planner that reads email, keeps a running database and document trail, and answers questions about where things stand — plus a separate loop that just deletes marketing mail.

Personal assistant

Local is for tinkering; Claude still does the real work

On a VRAM-constrained 5070 Ti, this person keeps local strictly in the 'learning and playing around' lane, and routes actual work through Claude with local models as a validation step at most.

Coding

The first local model this person actually trusts with real work

On a 12GB 5070, a heavily quantized Qwen 3.8 27B through a custom Hermes backend is, in their words, the first local model that's felt confidently productive.

Coding

Background coding at 10-15 tok/s on an Intel Arc laptop GPU

A NUC12 with a 16GB Intel Arc A770M handles a 262K-context Qwen build entirely in VRAM, coding in the background while the owner does something else.

Coding

Good enough for 80% of coding, honest about the other 20%

Daily local coding on a 4070 is explicitly not as good as Claude for complex refactoring — but the privacy and iteration speed still make it worth keeping.