@PlisSergey Not around to check gemma rn but before I stuck in the extra 32gb ddr5 I was getting 115t/s or slightly higher on qwen3.8-27b exl3 3.5bpw @ 262144 tok ctx.
cited on: qwen-3-8-27b
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.