Real-world
Business automation
Concrete workflows, including the tradeoffs and limitations reported by their authors.
this collection
Coaching elite athletes with a 2x DGX Spark cluster
A cycling and running coach runs client-facing coaching assistance on a small DGX Spark cluster, good enough for national-champion-level clients — at a cost the coach openly questions.
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.
A Hermes agent that turns email into ready-to-send invoices
A lightweight but daily setup: a Hermes agent on an M5 MacBook Pro reads morning email and prepares invoice PDFs with draft return emails.
Cancelling every cloud subscription after building a wiki anti-rot layer
A custom middleware layer that keeps an LLM-maintained wiki from decaying replaced this person's Google NotebookLM RAG setup entirely — and every cloud subscription along with it.
Great for transcribing calls, still not close enough for coding
Local transcription and summarization save real money at work, but this person draws a firm line at using local models for coding — even the newest ones.
Basic chat and organization on a Radeon 9070 XT
A Radeon 9070 XT handles basic chatbot, record-keeping, and organizational tasks, with a more capable local automation rig planned later.
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.
Daily agent workflows on an RTX 5090
An RTX 5090 runs recurring agents for project maintenance, site contributions and personalized news monitoring.
Building an agent stack locally before moving inference to the cloud
A product team developed their agentic tooling against local inference on a Strix Halo and midrange GPUs, then retargeted the same harness to cloud inference once it worked.
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.
Running sales work on GLM 5.3 Flash across two DGX Sparks, 200M tokens a week
A sales professional dropped every frontier subscription and runs work agents on two DGX Sparks, averaging about 200 million tokens per week.
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.
Every business app points at a local model on an RX 9060 XT
To keep email and business data away from cloud providers, this owner runs an abliterated Qwen 27B on an RX 9060 XT with a vision model on an old GTX 1650.
A job-matching agent that splits work between a local model and a cloud API
A Hermes agent searches job listings, does the easy keyword and summarisation work locally with Qwen 35B, then sends only the final analysis to a cloud model, cutting token use by about half.
Migrating a business's own cloud onto a Strix Halo with Hermes
A Hermes agent on a 128GB Strix Halo handles coding, open-source PRs, a docker-swarm-to-k8s migration and invoice processing on ERPNext.
A 2B local model behind 30+ private capabilities
A small GPU runs sub-10B models through Ollama, with a custom skill and memory layer driving a broad set of offline personal and automation workflows.
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.
Two RTX 5090s running helpdesk and ops for a small office
An 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.
A Tesla V100 32GB and an RTX 3090 on Strata: Qwen 3.8 Flash Next at 262K context for local business management
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 4x RTX 5090 (128GB) office rig serving a 50-person company: local RAG, chat, diffusion and agentic coding
A custom 4x RTX 5090 build with 128GB of VRAM, an Intel Xeon w5-3423 and 192GB of ECC DDR5 runs DeepSeek V4 Flash, Qwen 3.8 and Gemma 4 32B locally for a 50-person company that wants its data off grid.
Running a small e-commerce business on Qwen 3.8 27B
A cloned five-store e-commerce operation — cart, mailings, WhatsApp login, payment gateways — runs day to day on a single 7900XT, turning a real monthly profit.
Company email automation kept off the cloud for legal reasons
This company believes uploading user data to a cloud model would be illegal for their use case, so email and user-text automation runs on a Gemma 4 build on a single Radeon Pro AI R9700.
ISP NOC automation on two vLLM servers with 4× RTX 3090 each
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.