e0qdk@reddthat.com to LocalLLaMA@sh.itjust.worksEnglish · 3 months agoQwen3.8-27B Weights Releasedhuggingface.coexternal-linkmessage-square22linkfedilinkarrow-up174arrow-down12cross-posted to: hackernews@lemmy.bestiver.se
arrow-up172arrow-down1external-linkQwen3.8-27B Weights Releasedhuggingface.coe0qdk@reddthat.com to LocalLLaMA@sh.itjust.worksEnglish · 3 months agomessage-square22linkfedilinkcross-posted to: hackernews@lemmy.bestiver.se
minus-squarelunarwingorg@lemmy.worldlinkfedilinkEnglisharrow-up4·3 months agoHas anyone here really pushed the multimodal stuff with this yet? Been running this on a 4090 for over 24 hours and have been meaning to try out if its able to summarize images well, especially compared to something like qwen3vl on the same hardware
minus-squarelynx@sh.itjust.workslinkfedilinkEnglisharrow-up2·3 months agoCreating bounding boxes and OCR work both well. Creating an SVG of an image does not work well.
Has anyone here really pushed the multimodal stuff with this yet? Been running this on a 4090 for over 24 hours and have been meaning to try out if its able to summarize images well, especially compared to something like qwen3vl on the same hardware
Creating bounding boxes and OCR work both well. Creating an SVG of an image does not work well.