- 1 Post
- 12 Comments
Schilling2304@thelemmy.clubto
LocalLLaMA@sh.itjust.works•Opencode llama-server prefill/generation stats pluginEnglish
1·22 days agoYesterday I needed this. Will install this. Thanks.
May I ask: have you noticed if the prompt processing speeds shown in llama-bench are vastly different from llama-server ? I have hundreds of tokens of difference.
Schilling2304@thelemmy.clubto
LocalLLaMA@sh.itjust.works•Gemma4 12b released with "unified" approach to multi-modalityEnglish
1·28 days agoYou mean Gemma 4 ? You read in his discord ?
Schilling2304@thelemmy.clubOPto
LocalLLaMA@sh.itjust.works•My models don't have reasoning ability in llama-b9543 server but have in llama-cliEnglish
1·29 days agoI confirm the same and it works now. I set it to maximum because fewer reasoning effort tokens cuts it directly.
Thanks
Schilling2304@thelemmy.clubto
LocalLLaMA@sh.itjust.works•Gemma4 12b released with "unified" approach to multi-modalityEnglish
1·29 days agoI know it, seeing it in models titles.
Schilling2304@thelemmy.clubto
LocalLLaMA@sh.itjust.works•Gemma4 12b released with "unified" approach to multi-modalityEnglish
1·29 days agoIs uncensoring oneself a LLM difficult ?
Schilling2304@thelemmy.clubto
LocalLLaMA@sh.itjust.works•Gemma4 12b released with "unified" approach to multi-modalityEnglish
1·30 days agoDid you try any ? Because, I tried iglors and mradermacher, I got refusal to make a pipe bomb. Their answer are funny because they say to study academic engineering instead, lol. Still a refusal. I will try this one.
Schilling2304@thelemmy.clubto
Selfhosted@lemmy.world•This community isn't your personal adviserEnglish
1·1 month agoThe Arch Linux forum make people do that.
Schilling2304@thelemmy.clubto
Selfhosted@lemmy.world•This community isn't your personal adviserEnglish
18·1 month agoSomeone may have the same question in the future and there will be answers. You not responding is not that bad but it is even better that you do and provide an update to your situation, if you wish.
Schilling2304@thelemmy.clubto
LocalLLaMA@sh.itjust.works•would you laugh at me if I ran gemma-4-26b on a 4 core Xeon, with 32GB RAM, no GPU?English
1·1 month agoNo. In fact, that is nice. I should try.
Schilling2304@thelemmy.clubto
Open Source@lemmy.ml•Due to relentless AI scrapers notabug.org is currently down.
4·2 months agoWhere did you implement ? How did you add rate limits ? And you said “almost all”, who are those you can’t block ? Of course, you share if you want to. I don’t mind. Thanks.

Heard once a guy saying that no dick would reach the end… Another said that if it did, would it be floating in the void ?
lmao