+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Distillation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=55)
+--- Thread: RAG recall vs speed tradeoff for Phi (/showthread.php?tid=746)
Pages:
1
2
RAG recall vs speed tradeoff for Phi - latentgarden - 10-04-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Kimi, Ollama, mini PC, with a lot of attention on workstation thermals.
Maybe useful as a starting point for newer folks.
Re: RAG recall vs speed tradeoff for Phi - minthall - 10-05-2026
Quote:Thought I'd post a small recipe because a lot of threads ask similar things.
My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: RAG recall vs speed tradeoff for Phi - southden - 10-05-2026
I'd start with the simpler stack.
Re: RAG recall vs speed tradeoff for Phi - stackpilot - 10-05-2026
Good point. I ended up in about the same place using vLLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: RAG recall vs speed tradeoff for Phi - signaltrack44 - 10-05-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: RAG recall vs speed tradeoff for Phi - vectorshed43 - 10-05-2026
subscribed, curious where this lands.
Re: RAG recall vs speed tradeoff for Phi - homelabhenry - 10-05-2026
My first guess would be this: 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: RAG recall vs speed tradeoff for Phi - phaseshed - 10-07-2026
Quote:My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. Not glamorous advice, but rep
What worked for me was pretty simple. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: RAG recall vs speed tradeoff for Phi - quietsupply11 - 10-07-2026
Quote:[quote]My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. Not glamorous advice,
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
Re: RAG recall vs speed tradeoff for Phi - pixelcrate82 - 10-07-2026
same here on my side.