+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: LLM Models (https://www.datasculpting.ai/inference/forumdisplay.php?fid=12)
+--- Forum: Proprietary / Frontier (https://www.datasculpting.ai/inference/forumdisplay.php?fid=48)
+--- Thread: 70B still worth the pain: worth it? (/showthread.php?tid=998)
70B still worth the pain: worth it? - fastbench - 10-11-2026
I figured I'd ask here before changing everything.
I'm mostly working with Mistral in MLX on 4090. The part I'm trying to understand is KV cache pressure.
Would appreciate practical advice rather than theory.
Re: 70B still worth the pain: worth it? - torchsupply99 - 10-11-2026
Thanks, that helps. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: 70B still worth the pain: worth it? - vrampilot - 10-11-2026
Quote:Thanks, that helps. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more opti
Appreciate the detail. The pattern around MoE serving has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.