News for hackers. Stuff that matters.
Re:LFM2.5-24B-A2B: Built for Fast On-Device Agents by serf on Wednesday October 14, 2026 @08:50PM (#50097753)
>How many tokens/s do you need for a coding agent to feel like Claude or codex?

it's kind of a loaded question, this model gets a lot of tok/s but reasoning is forced on; the time-to-answer is really a combination of things like "how much does this thing want to over-reason" and "how much does this thing like tool use?" .

Re:LFM2.5-24B-A2B: Built for Fast On-Device Agents by nico on Wednesday October 14, 2026 @08:58PM (#50097808)
You are right, they are not exactly the same thing, just wanted to have a reference point

When running locally usually I have to trade off speed for a better model. I can run decently big models at about 2tk/s, or a pretty dumb one at 40-100tk/s

Re:LFM2.5-24B-A2B: Built for Fast On-Device Agents by serf on Wednesday October 14, 2026 @09:08PM (#50097887)
fwiw this thing puts out results very fast even on max reasoning.

the results i've gotten so far have been a little braindead though. still playing around. bad luck with traversing filesystems remotely so far.

it seems to want to make concluding decisions very fast regardless of reasoning levels.