Business automationGenesis archive2026-09
Daily agent workflows on an RTX 5090An RTX 5090 runs recurring agents for project maintenance, site contributions and personalized news monitoring.
Capacity range
Exact reported VRAM
Practice
Model
Quantization
Context length
Reported speed
Runtime
Tools / workflow (harness)
Record origin
EXPLORE BY CAPACITY
Start with your machine.
Capacity is the reported total for this setup. Multi-GPU and unified-memory layouts can behave differently.
8 GB or lessLaptops, iGPUs and modest cards9–12 GBEntry-level local inference13–16 GBCurrent mid-range cards17–20 GBRX 7900 XT and compact pro cards21–24 GB3090, 4090 and 7900 XTX class25–32 GB5090 and workstation cards33–48 GBWorkstation and multi-GPU setups49–96 GBLarge multi-GPU and datacenter setups97 GB+Unified memory, servers and clusters
6 resultsEvery record keeps its origin visible.
Regulated workGenesis archive2026-09
Legal work: a cloud planner driving local anonymisation, OCR and RAGA legal user has Claude build task plans while a local Qwen 27B executes them, with anonymisation, OCR for difficult documents and a RAG pipeline using nomic embeddings.
Business automationGenesis archive2026-09
A local-first portfolio tracker fed private financial documents all dayThree 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 automationGenesis archive2026-09
Two RTX 5090s running helpdesk and ops for a small officeAn office replaced roughly $2,000 a month of API consumption with two RTX 5090 machines running Qwen 3.8 27B under vLLM, one for helpdesk and one for ops.
CodingGenesis archive2026-09
Three concurrent coding sessions at 150 tok/s on one 5090A developer with 20 years of experience runs three concurrent coding sessions at about 150 tok/s each on a single RTX 5090 and has been cloud-free for three months.
Homelab opsGenesis archive2026-09
A daily-refreshed RAG advisor built from your own infrastructureA Python collector pulls read-only configs, firewall rules, and network health data every day and feeds it into a local RAG pipeline, so the advisor always knows the current state of the homelab without ever being able to touch it.