With 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.
in this range
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.
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.
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.
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.
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.
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.
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.
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.
Qwen3.8 Flash Next on a Radeon 7900XTX and 64GB DDR5 with Strata at about 60 tok/s
A Radeon 7900XTX with 24GB VRAM and 64GB DDR5 runs Qwen 3.8 Flash Next through Strata at about 60 tok/s up to 250k context while leaving VRAM for gaming.
My personal JARVIS
Personal life/project management agent with persistent memory, reminders, smart home duties (timers lights etc), computer use.
Qwen 3.8 27B on a single RTX 4090, measured (llama.cpp)
A documented, measured local coding setup: Qwen 3.8 27B on one RTX 4090 with llama.cpp and OpenCode, holding a 128k context and reporting around 92 tokens/s generation with speculative decoding.
Ternary Bonsai 2 27B on an RTX 4090: speed at a quality price
The same project's measured run of a ternary-quantised 27B model: about 92 tokens/s generation with no speculative decoding, from 6.7 GB of weights, at a documented cost in agentic coding ability.
GPT-6.1 Sol as cloud orchestrator with one RTX 3090 worker: wall clock and cost for three small builds
A single RTX 3090 running Qwen 3.8 27B Q4 via llama.cpp, orchestrated by GPT-6.1 Sol in the cloud, finished three small 3D games in 43.4 minutes and $0.17 total.
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.
Compare with another budget.
Every capacity guide, or start from your own machine and a task.