Comment by mirekrusin 16 hours ago 2x RTX 4090, Q8, 256k context, 110 t/s 1 comment mirekrusin Reply instagib 10 hours ago 1 4090, Qwen3.5-35B-A3B-UD-MXFP4_MOE, 64k context, 122 t/s. Llama.cpp
1 4090, Qwen3.5-35B-A3B-UD-MXFP4_MOE, 64k context, 122 t/s. Llama.cpp