Guia de IA Local

Rode IA de ponta no seu próprio hardware.

Privacidade total, zero custo por token. Do notebook zerado a um LLM rodando em cerca de 15 minutos.

Por que rodar IA localmente?

Privacy
Your prompts never leave your machine.
Zero cost
No API charges. No rate limits.
Offline
Works on a plane. Works in a bunker.
Full control
Pick the model, weights, system prompt.

Hardware necessário

Model sizeMinimum RAMRecommended GPUSpeed
3B – 8B8 GBNone / integrated20-50 tok/s CPU
13B – 27B16 GB8 GB VRAM (RTX 3060)15-30 tok/s
70B (quantized)32-48 GB24 GB VRAM (RTX 4090 / M3 Max)10-20 tok/s
405B64+ GB unifiedM3 Ultra or 2x A1005-10 tok/s

Apple Silicon punches above its weight thanks to unified memory. A 64 GB M3 Max runs Llama 3.3 70B faster than most $3,000 gaming GPUs.

Quantização e GGUF

A raw 70B model is roughly 140 GB. Quantization shrinks it by storing weights at lower precision (4-bit, 5-bit, 8-bit) with almost no quality loss for most tasks. The .gguf format is the community standard for quantized models.

A good default: Q4_K_M. It cuts size by ~4× while preserving 98%+ of the quality.

Escolha seu runner

Ollama
One-line install. CLI + API. The default for hackers.
ollama.com
LM Studio
Beautiful GUI. Best for beginners.
lmstudio.ai
Open WebUI
Self-hosted ChatGPT clone. Multi-user.
openwebui.com
AnythingLLM
RAG + docs on top of local models.
anythingllm.com

Quickstart de 15 minutos com Ollama

  1. 1Install Ollama from ollama.com. macOS, Linux and Windows supported.
  2. 2Open a terminal.
  3. 3Run: ollama pull llama3.3 — this downloads a 40 GB quantized model.
  4. 4Run: ollama run llama3.3 — start chatting.
  5. 5For a ChatGPT-like UI, install Open WebUI and point it at localhost:11434.

Melhores modelos locais agora