v1.1.9 — x64 installer (.exe or .msi)
| OS | Windows 10 (64-bit) or newer — Windows 11 recommended |
| Architecture | x86_64 (64-bit) |
| RAM | 4 GB minimum — 8 GB recommended |
| Disk space | 300 MB free |
| USB | USB port for serial communication; driver depends on adapter (e.g. CH340, CP2102, FTDI) |
| WebView2 Runtime | Preinstalled on Windows 11; automatically installed on Windows 10 if missing |
The serial terminal, macros, triggers, scripting, and programmer work without any GPU. Running your own local model through AI Assistant (BYOK) is the demanding part and needs a high-VRAM GPU. During testing, models below roughly 20B parameters could not drive the assistant's tools reliably, 20-30B is the lower edge of usable, and confident results start above 100B.
| GPU | Any Vulkan-capable GPU — NVIDIA, AMD (recent), Intel Arc |
| Entry (below usable) |
16 GB VRAM — 20B-class models (Q4); below the range where the assistant works reliably |
| Recommended | 24 GB VRAM (e.g. RTX 3090 / 4090) — 20-30B models (Q4-Q5); lower edge of usable |
| High-end | 48 GB+ VRAM (single card or two of them) — 70B and larger; 100B+ (Q4) needs about 64 GB |
| Drivers | A current graphics driver with Vulkan support — NVIDIA, AMD and Intel drivers all include it |
CPU-only is technically possible but extremely slow at these sizes — a dedicated GPU is strongly recommended. During testing, models below roughly 20B parameters could not drive the assistant's tools reliably.
The assistant can be wrong. Language models misread frames, invent register numbers and write plausible code that does the wrong thing. Read what it proposes before you send it to a device — a bad Modbus write or a wrong firmware flash can damage equipment or stop a machine.