Full directory
GUIDE BY CAPACITY

With 21–24 GB,
here is what really runs.

Experiences reported by people using their machines every day. The figure is the reported setup capacity; multi-GPU and unified-memory layouts can behave differently.

14documented uses
in this range
Documents

Grading 500 student exams with a local model

A teacher runs an entire exam-correction pipeline on a single 3090, from generating answer sheets to scoring hundreds of students automatically.

Batch utility

Video cropping, UI bug fixes, and news roundups on a 24GB card

A detailed personal checklist for getting a local setup to a genuinely reliable state — quant choice, inference engine by OS, and only then, real tasks.

Coding

Full app development on a single 3090 with OpenCode

A four-bit Qwen 3.8 quant at 200K context handles complete app builds through OpenCode, left running until it hits a decision point.

Business automation

PR review and support triage on two budget RTX 3060s

Two 12GB 3060s handle both code review and customer-support lookups, reasoning read-only over live account data and internal docs.

Documents

A daily document and writing workflow on a 24GB Mac, wrapped in a desktop app

Rather than chatting with a local model, this user runs local document Q&A, summarisation, translation and grammar correction on an M4 Pro, then built a desktop app to tie the pieces together.

Business automation

A local-first portfolio tracker fed private financial documents all day

Three GPUs spread across machines run Qwen 3.8 27B through a custom stateful agent layer to build a personal finance and portfolio tracker without shipping documents to the cloud.

Business automation

Construction estimating work moved onto a 7900XTX and two DGX Sparks

After six months of tinkering, Qwen 3.8 27B justified a 7900XTX plus two DGX Sparks, taking over a job the estimating team was spending dozens of hours a week on.

Batch utility

Processing thousands of in-game documents to build roleplay casefiles

Playing a detective in a large GTA V roleplay server, this person used a local model to turn thousands of in-game arrest reports and applications into structured criminal profiles.

Business automation

Internal company tools on a scavenged 1TB ECC server with mixed GPUs

A self-built server with 1TB of ECC RAM and a mix of used 3090s and P100s produced internal tools whose economic impact is reported at ten times the hardware cost.

Business automation

Running a website with Qwen 27B on a 7900XTX

A local Qwen model maintains a website, answers email and runs recurring jobs on a dedicated Radeon workstation.

Regulated work

Unit tests and reviews for NDA-bound client code on a single 3090

A contractor whose clients forbid commercial providers from reading their source code runs unit tests and code reviews locally on a 3090, with a long-context llama.cpp setup.

Coding

Fitting Qwen 27B and a 96K context onto a single 3090

A 3090 owner runs Qwen 3.8 27B daily in Cline at a 96K context by quantising the KV cache to q8_0, reporting about 43 tok/s once the model stops thinking.

Coding

A llama.cpp fork reaching 90+ tok/s through a 100K context on a 3090

A custom llama.cpp fork for Ampere cards pushes Qwen 3.8 27B to 90+ tok/s through a 100K context, aimed at caching-heavy agentic work.

Batch utility

Generating 60,000 helpdesk tickets overnight instead of burning API credits

A 3080 churned for about 18 hours to produce roughly 60,000 synthetic helpdesk tickets, complete with email threads and time entries, for testing a ticketing system.