CatGPT@lemmy.dbzer0.com to LinkedinLunatics@sh.itjust.works · edit-22 months agoBane Masklemmy.dbzer0.comimagemessage-square255linkfedilinkarrow-up1691arrow-down15 cross-posted to: programmer_humor@programming.dev
arrow-up1686arrow-down1imageBane Masklemmy.dbzer0.comCatGPT@lemmy.dbzer0.com to LinkedinLunatics@sh.itjust.works · edit-22 months agomessage-square255linkfedilink cross-posted to: programmer_humor@programming.dev
minus-squarecass80@programming.devlinkfedilinkarrow-up1·2 months agoWhat’s your model of choice? I want to try to get away from Claude and move it to a local model.
minus-squaresave_the_humans@leminal.spacelinkfedilinkEnglisharrow-up2·2 months agoFrom what Ive heard Opencode, for agentic coding, is great, and I’d maybe try Gemma 4 (googles open weights model - permissive Apache 2.0 licensed) locally if I was so inclined. The size should be great for consumer hardware.
minus-squaremorrowind@lemmy.mllinkfedilinkarrow-up2·2 months agoClaude? Claude doesn’t support audio input. I’m talking about transcription models. I use Parakeet v2
What’s your model of choice? I want to try to get away from Claude and move it to a local model.
From what Ive heard Opencode, for agentic coding, is great, and I’d maybe try Gemma 4 (googles open weights model - permissive Apache 2.0 licensed) locally if I was so inclined. The size should be great for consumer hardware.
Thank you!
Claude? Claude doesn’t support audio input. I’m talking about transcription models. I use Parakeet v2