context size vs speed in GGUF on M3 Max

[vrambandit]

Thanks, that helps. I ended up in about the same place using Ollama. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[macronest]

worth checking the driver first.

[visionyard23]

That matches what I was seeing. 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.

[embershed99]

worth checking the driver first.

[vrambandit]

Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The surprise was that memory pressure showed up before throughput collapsed. I keep promising myself this is the last rebuild.

[mangotinker73]

that fixed it for me too.

[bytesupply76]

Posting this in case it saves someone else a little time.

If you were starting from scratch today for this use case, what would you choose first and what would you ignore?

Would rather learn from your scars than collect my own all at once.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[latentcraft]

that fixed it for me too.

A couple things I'd check first. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[mintstream9]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. Once you know the plain path works, then add the faster path back in piece by piece.