best sandbox for trying risky tools for DeepSeek

[syshouse]

Has anyone else run into this?

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling workstation thermals.

Not looking for the perfect answer, mostly what worked in real use.

[circuitworks90]

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.

[fastquill74]

I'd approach it in a boring order. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

[torchsupply99]

My first guess would be this: On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

[syshouse]

Need a little more detail here. Is this local-only or are you routing anything externally?

[sanescope]

Need a little more detail here. Is this local-only or are you routing anything externally?

Interesting, I hadn't tried that. I ended up in about the same place using MLX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[mangofield33]

Good point. I ended up in about the same place using llama.cpp. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[stackarch]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.