A small ISP (~7,600 customers) serves its agentic operations work on two identical machines, each with 4× RTX 3090 (250W-capped) and vLLM v0.30.0; llama-benchy measures ~5993 tok/s prefill and ~199 tok/s generation.
Start with your machine.
Capacity is the reported total for this setup. Multi-GPU and unified-memory layouts can behave differently.
Two single-GPU Ubuntu servers, one with a blower-modded Tesla V100 32GB and one with an RTX 3090, run Strata with Qwen 3.8 Flash Next at 262K context for local business management automation.
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.
A two-3090 local setup runs Qwen 27B for coding and infrastructure work, including bug fixing and quality-of-life automation.
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.
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.
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.
A self-hosted AI ecosystem spans two Linux servers, assigning different GPUs to long-context coding, inference, speech, RAG and media workloads.
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.
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.
A developer uses Qwen 3.8 27B for primary coding on a 3090-plus-5060 setup and pays for frontier inference only when speed or model depth matters.
A teacher runs an entire exam-correction pipeline on a single 3090, from generating answer sheets to scoring hundreds of students automatically.