REQUIREMENTS
System Requirements โ BOM AI
BOM AI runs on your computer. The more powerful the machine, the faster and smarter it gets
Minimum for Every Model
| Item | Minimum |
|---|---|
| Operating system | Windows 10/11 64-bit ยท macOS 12+ ยท Ubuntu 22.04+ |
| RAM | 8 GB |
| Disk space | 10 GB free (including models) |
| Internet | Only for the first download |
| GPU | Optional, but highly recommended |
Recommended GPU per Model
๐ข Light โ GPU 4-6 GB (or no GPU)
Model: Gemma-3 4B (~2.5 GB) ยท Thai chat + image reading + translation
Example cards: NVIDIA GTX 1660 ยท RTX 3050 ยท RTX 4060
Best for: everyday laptops โ Thai chat + translation
No GPU at all? It still works โ the CPU is slower but every feature is included ยท Typhoon 2-5 / Chinda (~3 GB โ CPU)
๐ก Mid โ GPU 8-12 GB
Model: MiMo 9B (~5.5 GB) ยท best search
Example cards: RTX 3060 12GB ยท RTX 4060 Ti ยท RTX 4070 ยท RTX 5060 Ti
Best for: typical desktops โ everything plus image reading (Vision)
โญ Recommended: MiMo 9B ยท best search
๐ฃ Full โ GPU 16 GB+
Model: GLM-4.7 12B (~7.5 GB) ยท 709-L 27B (~16 GB โ GPU 24 GB+)
Example cards: RTX 4080 ยท RTX 4090 ยท RTX 5070 Ti ยท RTX 5080
Best for: workstations/gaming rigs โ deepest and smartest answers
๐ Champion: GLM-4.7 12B โ 62.2/70
Why a Graphics Card?
AI models work by computing billions of matrix operations. GPUs (graphics cards) are designed exactly for this kind of math โ 10-50x faster than CPUs
The smarter the model, the more parameters it has, and the more VRAM (memory on the graphics card) it needs. That is why graphics cards are expensive โ they genuinely matter for AI
| Model size | Parameters | VRAM used | Response speed |
|---|---|---|---|
| 4B | 4 billion | ~2.5 GB | Very fast |
| 8-9B | 8-9 billion | ~5.5 GB | Fast |
| 12B | 12 billion | ~7.5 GB | Moderate |
| 27B | 27 billion | ~16 GB | Moderate |
You choose the model โ all 6 models
BOM AI ships 6 models and you pick the one you want. The app detects your GPU at startup and recommends a good fit, but the choice is yours.
How to Check Your GPU
Windows: Press Ctrl+Shift+Esc โ Performance tab โ GPU to see the model name and VRAM
macOS: Apple menu โ About This Mac โ check Graphics
Linux: Open Terminal and type nvidia-smi (if you have NVIDIA) or lspci | grep VGA