v0.1.18 — x64 AppImage
| OS | Ubuntu 22.04+ / Debian 12+ / Fedora 38+ or any modern 64-bit Linux distro |
| Architecture | x86_64 (64-bit) |
| RAM | 4 GB minimum — 8 GB recommended |
| Disk space | 300 MB free |
| USB | USB port for serial communication |
| Dependencies | WebKit2GTK 4.1 (preinstalled on most distros; if missing: sudo apt install libwebkit2gtk-4.1-0) |
The serial terminal, macros, triggers, scripting, and programmer work without any GPU. Local AI models that are powerful enough for ComIO.Studio (code generation, log analysis, MCU debugging) require a high-VRAM GPU. Smaller models (under ~13B parameters) are too weak for reliable assistance — we do not recommend them.
| GPU | NVIDIA (CUDA) or any Vulkan-compatible GPU (AMD recent, Intel Arc) |
| Minimum (usable assistant) |
16 GB VRAM — runs gpt-oss 20B (Q4 quantization), Gemma 4 26B (low quant) |
| Recommended | 24 GB VRAM — runs Gemma 4 31B comfortably (Q4-Q5), better context length |
| High-end | 48 GB+ VRAM (RTX 6000 Ada, dual 24GB) — 70B-class models, large context |
| Drivers | NVIDIA: driver 520+ with CUDA 12 (for CUDA backend) Any GPU: Vulkan driver installed |
CPU-only is technically possible but extremely slow for 20B+ models — dedicated GPU is strongly recommended.
| 1. Download | Download the .AppImage file |
| 2. Make executable | chmod +x ComIO.Studio-x86_64.AppImage |
| 3. Run | ./ComIO.Studio-x86_64.AppImage |
AppImage is self-contained — no installation required. You can place it anywhere on your system.