Q4 で 73 モデル · 24 GB 枠

Local AI models for 24GB VRAM

24 GB is the enthusiast sweet spot. 30B dense models fit, mid-size mixture-of-experts become usable, and local image or short video generation is realistic.

典型的な構成： 30B dense models, mid-size MoE, or local video. · 例：RTX 4090

サイズは Q4_K_M に少しのランタイムオーバーヘッドを加えた値です。お使いのマシンで全カタログを評価または特定の GPU を選ぶ.

Common questions

What models can an RTX 4090 run locally?
Almost every popular open chat and coding model at high quality, plus FLUX-class image generation and the lighter video checkpoints.