AIXDAabout 3 hours ago
Qwen 3.6 Runs Complex Coding on RTX 5080
1 min read
Qwen 3.6 generated a working Python file-organizing script on an RTX 5080, Ryzen 7 9800X3D, and 32GB RAM in about three minutes. The 35B MoE model runs locally via Ollama at 68.93 tokens per second, keeping data off the cloud.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
