Post #3910672
2026-07-18 12:45 UTC
@scottjenson@social.coop Yeah, it's VERY slow. Like literally unusable slow. If you're trying to get off the Claude/Codex train I'd look at GLM/Kimi but it's still subscription.
Really good coding agents aren't YET self hostable on "consumer" devices. And if somebody says it's not true they're either lying or have 196GB RAM Mac and are trying to say it's consumer electronic because you can buy it in the store.
Replies (1)
-
@awax@datasci.social 2026-07-18 13:01
@pawel@wspanialy.eu I wouldn't say *unusably* depending on how you use them and how many tokens per second it actually runs. I've only used them occasionally in chat mode for helping me design individual classes based on specification, and 2-4 minutes for 8k-12k token responses was fine for me.