70B still worth the pain with llama.cpp

[amberpatch25]

Good point. That matches what I saw on mini PC. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[llm_wren]

Interesting, I hadn't tried that. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[mellowsupply]

same here on my side.

[mintstation99]

A couple things I'd check first. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[orbitbench6]

A couple things I'd check first. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of

What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[cacheline]

Can you fill in a bit more context? Is this local-only or are you routing anything externally?