Qwen 30b MoE - 30tps - 6GB vram - Done!

So, I have been dreaming of getting 17 tokens per second using my RTX 3050 6GB version on a decent context window for Hermes needed above 60k. The hope is that has was a 22GB of DDR 4, hoping they can take some of those experts and give me room for context. What did I get 10 or less tokens per

中文全文翻译正在补齐，可先查看下方英文原文。

So, I have been dreaming of getting 17 tokens per second using my RTX 3050 6GB version on a decent context window for Hermes needed above 60k. The hope is that has was a 22GB of DDR 4, hoping they can take some of those experts and give me room for context. What did I get 10 or less tokens per