0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

24GB GPU(RTX 3090/4090/RX 7900 XTX)でローカルLLMは何が動く?数字で確認

0
Posted at
  • 4Kコンテキストで、129モデル中97が24GBに快適に収まり、102が一応ロード可能。
  • 同じ24GBでも速度は帯域次第:Tesla P40の346 GB/sからRTX 4090の1,008 GB/sまで。生成速度はおおよそ「帯域 ÷ 重みファイルサイズ」。
  • Qwen3.8 27B:Q4_K_Mで約18.5GB(4K)、残り約5.5GBをコンテキストに。Q5_K_M(約22.2GB)はギリギリ。
  • 24GBのMacはGPUが使えるのが約4分の3なので別扱い。
  • 70BクラスはQ4_K_M・8Kで約47.5GB、24GB一枚では無理(2枚かオフロード)。
    自分の構成で確認するなら無料のVRAM計算機(登録不要):https://quantized.uk/tools/vram-calc/ 、詳しいガイド:https://quantized.uk/cookbook/24gb-gpu-what-to-run/
0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?