←back to thread

Show HN: oLLM – LLM Inference for large-context tasks on consumer GPUs

(github.com)
3 points anuarsh | 1 comments | 28 Aug 25 23:19 UTC | HN request time: 0.204s | source
Show context
attogram ◴[29 Aug 25 00:43 UTC] No.45058682[source]▶
"~20 min for the first token" might turn off some people. But it is totally worth it to get such a large context size on puny systems!
replies(1): >>45058870 #
anuarsh ◴[29 Aug 25 01:09 UTC] No.45058870[source]▶
Absolutely, there are tons of cases where interactive experience is not required, but ability to process large context to get insights.
replies(1): >>45061478 #
1. attogram ◴[29 Aug 25 08:09 UTC] No.45061478[source]▶
It would be interesting to see some benchmarks of this vs, for example, Ollama running localy with no timeout