Torment Nexus: https://youtu.be/W_Qlb85JD_g

Lol wait time out - did you not mean to make a don quixote joke there? I thought it was a pretty clever counterpart to the whole "sisyphean task" thing so I figured it was safe to borrow from the work, casting myself as the ploughman and you as Quixote... sorta an evening of the tragic comedy, as it were.

I feel like you definitely can get away with as much as even 5, but if you actually look at the CLI, it will tell you how many draft tokens actually got accepted. In some situations like writing simple text, over 90% of my two draft tokens get accepted so setting it to five would have made it faster. However if you run a task which requires heavy reasoning, even two draft tokens start approaching close to only 60%. Considering Qwen3.8-27B overthinks more than an anxious teenage girl, you should generally with two. If you take my example with the quant dropped to UD-Q5_K_XL with 262K tokens and reasoning low for a task that isn't actually complex, just long, then go right ahead and let it run with 5.

Was it written by AI?

Interesting, the startup costs would be much larger; however considering there is less wear this investment will pay off quite quickly.

I've yet to see them fire a shot. Americans are too busy exhausting their multi-trillion dollar military budget playing wack-a-mole with Iranian drone operators