Hardware Requirements
RAM and GPU requirements for different AI models.
Understanding Requirements
EdgeNote AI uses two types of AI models that run simultaneously. Your available RAM determines which model combinations you can use effectively.
8 GB RAM
Basic
Small Whisper + 1.7B LLM. Good for English, basic summaries.
16 GB RAM
Recommended
Medium Whisper + 4B LLM. Excellent quality for most use cases.
32 GB+ RAM
Maximum
Large Whisper + 8B-14B LLM. Best quality, all languages.
Whisper Models (Transcription)
Whisper models convert speech to text. Larger models are more accurate but require more RAM.
| Model | Size | RAM Required | Languages | Notes |
|---|---|---|---|---|
Whisper Tiny | 77 MB | 1 GB | English | Ultra-fast, lower accuracy |
Whisper Small | 488 MB | 2 GB | English | Fast with good accuracy |
Whisper MediumRecommended | 1.5 GB | 4 GB | English | Excellent accuracy |
Whisper Large V3 Turbo | 1.6 GB | 4 GB | 99 languages | Fast + multilingual |
Whisper Large V3 | 3.1 GB | 6 GB | 99 languages | Maximum accuracy |
LLM Models (Summarization)
LLM models generate summaries and extract insights. Larger models produce better quality output.
| Model | Size | RAM Required | Notes |
|---|---|---|---|
Qwen 3 1.7B | 1.4 GB | 2 GB | Lightweight and fast |
DeepSeek R1 1.5B | 1.1 GB | 2 GB | Fast with reasoning |
Gemma 2 2B | 1.6 GB | 4 GB | Compact and efficient |
Phi-3.5 Mini 3.8B | 2.4 GB | 4 GB | Balanced performance |
Llama 3.2 3B | 2.0 GB | 4 GB | Fast and reliable |
Qwen 3 4BRecommended | 2.6 GB | 4 GB | Best for most desktops |
Mistral 7B | 4.4 GB | 12 GB | Fast inference |
DeepSeek R1 7B | 4.7 GB | 12 GB | Excellent reasoning |
Llama 3.1 8B | 4.9 GB | 12 GB | General purpose |
Qwen 3 8B | 5.2 GB | 16 GB | Superior quality |
Gemma 2 9B | 5.8 GB | 8 GB | Strong performance |
DeepSeek R1 14B | 9.0 GB | 16 GB | Best reasoning |
Phi-4 14B | 9.1 GB | 16 GB | State-of-the-art |
Recommended Combinations
| RAM | Whisper Model | LLM Model | Total Size | Best For |
|---|---|---|---|---|
| 8 GB | Whisper Small | Qwen 3 1.7B | ~2 GB | Quick notes, English only |
| 16 GB | Whisper Medium | Qwen 3 4B | ~4 GB | Most users (recommended) |
| 16 GB | Large V3 Turbo | Qwen 3 4B | ~4 GB | Multilingual meetings |
| 24 GB | Whisper Large V3 | DeepSeek R1 7B | ~8 GB | Complex analysis |
| 32 GB+ | Whisper Large V3 | Phi-4 14B | ~12 GB | Maximum quality |
Memory Usage
RAM requirements listed are for the models alone. Your system also needs RAM for the operating system and other applications. Leave at least 4GB free for optimal performance. EdgeNote AI will warn you if a model exceeds your available memory.