Qwen3.6-35B-A3B Q6_K · 8 streams on 8 slots · ik_llama.cpp 11.4 tok/sprefill 858 tok/s qwen3.6-35b-a3b ik_llama.cpp7cd62a3eUD-Q6_K35B · 3.5B activeP5661 · G74 · cache 0% · min 64ctx 8kfa onrtx-3090rtx-a6000linux8 streams! 5 caveats midagedev 2026-09-20
Qwen3.6-35B-A3B Q6_K · 1 stream · ik_llama.cpp 125 tok/sprefill 2734 tok/s qwen3.6-35b-a3b ik_llama.cpp7cd62a3eUD-Q6_K35B · 3.5B activeP7248 · G5271 · cache 0%ctx 32kfa onrtx-3090rtx-a6000linux1 stream! 2 caveats midagedev 2026-09-20
The README hero: four code-review questions at once 70.9 tok/sprefill 1097 tok/s qwen3.6-35b-a3b ik_llama.cpp7cd62a3eUD-Q6_K35B · 3.5B activeP6065 · G603 · cache 0% · min 597ctx 8kfa onrtx-3090rtx-a6000linux4 streams! 4 caveats midagedev 2026-09-20