🤯 A localmaxxer hit ~381 tok/s on a SINGLE RTX 3090 with Qwen3.8-27B. This developer has turned a 24GB RTX 3090 into a monster Qwen inference box - w/some creativity. Four days ago 👉 ⚡ ~82 tok/s single-user Then 👉 ⚡ ~114 tok/s with optimized MTP ⚡ ~138 tok/s with DFlash2