Local LLM Performance Using a Combination of RTX 5080 and RTX 3090

인프라/플랫폼 | Sun Jun 14 2026 00:00:00 GMT+0000 (Coordinated Universal Time) | 1 sources

A setup case demonstrated running the Qwen 3.6 27B Q8 model at over 80 tokens per second in a hardware environment combining an RTX 5080 and an RTX 3090.

Sources

• [1] RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8 - Hacker News