Machine Learning
Local LLMs 2026: Technical Reference Guide
Hardware Target: 24GB VRAM (RTX 3090 / 4090)All model sizes sourced directly from Ollama’s model library (Q4_K_M unless noted). Model Lineup Model Ollama Tag Total Params Active Params Architecture Ollama Size (Q4_K_M) Nemotron 3 Nano 4B nemotron-3-nano:4b 4B 4B Hybrid Mamba 2.8 GB Qwen 3.5 9B qwen3.5:9b 9B 9B Dense Read more