CodingGenesis archive2026-09
A senior engineer with no need for cloud on a 64GB Strix HaloAn experienced software engineer runs Qwen3-Coder 30B on a 64GB Strix Halo and finds local working better than newer, larger models for well-scoped tasks.
Capacity range
Exact reported VRAM
Practice
Model
Quantization
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
2 resultsEvery record keeps its origin visible.
Homelab opsGenesis archive2026-09
Local coding for a homelab app, with ChatGPT as the second reviewerQwen3-Coder through Cline writes the app; a paid ChatGPT Plus subscription reviews the prompts and the output before it ships.