SKIP TO CONTENT
Todos os artigos
INFRASTRUCTURE·May 5, 2025·7 MIN DE LEITURA

2025 Open-Weight Benchmarks: When to Choose Small, Local, or Frontier

Por Rowan Li

The numbers

  • Llama 3 70B Instruct (quantized) hit 140ms P95 on-device for summarization with receipts.
  • DeepSeek Coder V2 matched GPT-4 Turbo on repo-understanding tasks while costing ~38% less.
  • Frontier models still win on speculative planning and multi-hop reasoning—but only when paired with eval gates.

Decision guide

  • Choose small/local for privacy-first flows and deterministic latency.
  • Choose open-weights in the cloud for cost-sensitive CRUD and summarization.
  • Choose frontier for greenfield features where correctness > cost and you can afford eval overhead.

Starter configs

Included: Terraform modules for split inference (edge + cloud), prompt lint rules for open weights, and receipts dashboards that show which model handled each call.

Build Blueprint · Creator

Tem uma ideia? Receba a especificação a partir da qual seu agente de IA pode construir.

Descreva qualquer produto e receba um blueprint de construção completo — stack, modelo de dados, telas, APIs e um prompt pronto para colar no Claude Code ou Cursor. Exporte para PDF.

Abrir o Blueprint