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.
in this range
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.
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.
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.
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.
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.
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.