+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Context / KV Cache (https://www.datasculpting.ai/inference/forumdisplay.php?fid=41)
+--- Thread: draft model choices: early impressions (/showthread.php?tid=774)
Pages:
1
2
Re: draft model choices: early impressions - cacheline - 10-10-2026
Not sure I agree there. I get why that seems right, but on A6000 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.
Re: draft model choices: early impressions - cozysmith - 10-13-2026
Appreciate the detail. The pattern around tool calling has been pretty similar for me.
Re: draft model choices: early impressions - cacheline - 10-16-2026
Interesting, I hadn't tried that. I ended up in about the same place using llama.cpp. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: draft model choices: early impressions - deltagrid - 10-16-2026
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. Not glamorous advice, but repeatable baselines save a lot of time. Turns out 'just one more test' was a lie.