working config for 32k context for FLUX

[cachebench]

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with embeddings.

Curious whether that lines up with what other people are seeing.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

[mangoquill]

I'd start with the simpler stack.

[cudapoint]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[vramstream]

I'd start with the simpler stack.

[mangoquill]

A couple things I'd check first. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[rocmriley]

What exact setup are you running? Are you testing this on mini PC or something else?

[audioriver]

Appreciate the detail. 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.

[batchshed]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there.

[deltagrid]

Can you fill in a bit more context? What model, what runtime, and roughly what context size?

[cachebench]

What exact setup are you running? What model, what runtime, and roughly what context size? At this point the real bottleneck is my patience.