Why your local LLM feels dumber than it is (forum.level1techs.com)
jonplackett 2 hours ago
prettyblocks an hour ago
downrightmike an hour ago
lukan an hour ago
jonplackett an hour ago
But I’m having a lot of luck just running things when I’m away from the computer and can leave it plugged in.
It starts going weird (unreliable and slow) with context over 80k so you have to pick tasks one at a time and baby sit a lot more than Claude. But it really is very capable and feels like there’s an intelligence there to talk to. Maybe gpt-4 level clever?
I have an m5 max 64gb and I think anything slower would be quite painful.
StarlaAtNight an hour ago
chorlton2080 an hour ago
jonplackett an hour ago
dominotw 5 minutes ago
Gareth321 an hour ago
alexpotato 35 minutes ago
- find a free GPU droplet on digital ocean
- fire it up
- pull in a snapshot of the model + extra files/packages etc
- set up a ssh tunnel so that the localhost:8000 routes to the above
Then I just configured OpenCode to use the above and was off to the races.
Works out to be about ~$2/hr all said and done which isn't bad as I only pay when I'm using it (but could get expensive with 24/7 running)
alexchantavy an hour ago
dominotw 29 minutes ago
mattdw 8 minutes ago
Edited to add: for agentic workflow I’m running omlx which tells me it has about a 90% cache hit rate (tradeoff is some disk and mem space) - that noticeably changes the felt speed.
MrScruff 5 minutes ago
applicative an hour ago
system2 7 minutes ago
JacobJack 30 minutes ago
Genuine question : is there something fundamentally wrong with Ollama ?
I use Ollama because it is easy to set up and manage (and also because VLLM is not super Windows friendly).
I thought the main advantage of VLLM was better concurrency management (better batching).
But if the quality of the interference itself is an issue, then maybe I should reconsider my choice.
kangalioo 21 minutes ago
b112 8 minutes ago
And it did in that case make a significant difference.