Skip to content

Instantly share code, notes, and snippets.

@MuhammadQuran17

MuhammadQuran17/graphic_vide_cards_cheatsheat.md

Last active May 22, 2025 05:46
Show Gist options
  • Save MuhammadQuran17/9d720ef9126c6a2fd22e3ec8c8537f84 to your computer and use it in GitHub Desktop.
Save MuhammadQuran17/9d720ef9126c6a2fd22e3ec8c8537f84 to your computer and use it in GitHub Desktop.
Download ZIP
Graphic Video Cards CheatSheat
Raw
graphic_vide_cards_cheatsheat.md

Check on Windows

  • Go to Nvidia Control Panel
  • Press Help
  • Press system Information
Тип памяти Объяснение
Dedicated Video Memory Это реальная физическая VRAM, встроенная в видеокарту. У тебя 4 ГБ.
Shared/System Memory Это обычная оперативная память (RAM), которую система может одолжить видеокарте.
Total Available Graphics Memory Это сумма dedicated + shared. У тебя 4 ГБ + 16 ГБ = 20 ГБ.

Quantization of AI models

  • Standart 32 bit
  • GGUF is better then GGML, and its newer one, that tackles GGML previous drawbacks. GGUF is a file format for storing models for inference with GGML and executors based on GGML. GGUF is a binary format that is designed for fast loading and saving of models, and for ease of reading. Models are traditionally developed using PyTorch or another framework, and then converted to GGUF for use in GGML. It is a successor file format to GGML, GGMF and GGJT, and is designed to be unambiguous by containing all the information needed to load a model. It is also designed to be extensible, so that new information can be added to models without breaking compatibility.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment