+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: llama.cpp / GGUF (https://www.datasculpting.ai/inference/forumdisplay.php?fid=35)
+--- Thread: context size vs speed in GGUF: setup advice (/showthread.php?tid=997)
Pages:
1
2
Re: context size vs speed in GGUF: setup advice - northcraft90 - 10-17-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: context size vs speed in GGUF: setup advice - batchpeak - 10-17-2026
same here on my side.
Re: context size vs speed in GGUF: setup advice - vrambandit - 10-17-2026
I'd start with the simpler stack.
Re: context size vs speed in GGUF: setup advice - pixelcrate82 - 10-18-2026
Good point. That matches what I saw on M3 Max. The biggest change for me was simplifying the stack instead of adding one more optimization layer.