Homelab opsGenesis archive2026-09
Coding and homelab maintenance on a dual-R9700 serverA garage server with two Radeon Pro AI R9700 cards supports coding, homelab maintenance and an evolving Cline/Open WebUI workflow.
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
7 resultsEvery record keeps its origin visible.
CodingGenesis archive2026-09
One R9700 with card-specific kernels for local codingA single Radeon Pro AI R9700 runs coding work using Lucebox and a recommended 4-bit quant, relying on custom optimized kernels for the card.
Hybrid orchestrationGenesis archive2026-09
The minimum setup for a genuinely useful local agentAfter experimenting, this user argues a real computer-manipulating agent needs at least a Strix Halo plus an oculink R9700, or a DGX Spark plus a second GPU for auxiliary models.
Hybrid orchestrationGenesis archive2026-09
An orchestrator dispatching to five fresh-context subagentsA custom harness layers a written skill and an orchestrator agent that dispatches tasks to five subagents, each starting from a clean context with hard test gates.
Business automationGenesis archive2026-09
Company email automation kept off the cloud for legal reasonsThis 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.
CodingGenesis archive2026-09
Using a local model to stress-test the agent a coding agent is buildingAn unusual layered setup: the local model isn't the coding agent — it's the thing an outer coding agent uses to build and stress-test a separate 'inner' agent.
Hybrid orchestrationGenesis archive2026-09
A local model and Codex reviewing each other's work, with a hard stop on disagreementThe same Qwen 3.8 27B instance that drives this person's Hermes agent also sits as an MCP tool for Codex, reviewing its proposals and its final output — and the task simply stops if the two can't agree.