panos@catodon.rocks to Technology@lemmy.worldEnglish · 22 hours agoAnthropic logged net loss of over $80 billion in first half of 2026www.reuters.comexternal-linkmessage-square225linkfedilinkarrow-up1843arrow-down12
arrow-up1841arrow-down1external-linkAnthropic logged net loss of over $80 billion in first half of 2026www.reuters.companos@catodon.rocks to Technology@lemmy.worldEnglish · 22 hours agomessage-square225linkfedilink
minus-squareelucubra@sopuli.xyzlinkfedilinkEnglisharrow-up1·6 hours agoHow do you run qwen 3.8 flash next on 16gb vram, if you don’t mind me asking ?
minus-squarejaschen306@sh.itjust.workslinkfedilinkEnglisharrow-up1·55 minutes agohttps://github.com/niko1221/strata The model I’m using is a Q4. Unsloth UD-IQ4_XS
minus-squareSeralth@piefed.seralth.comlinkfedilinkEnglisharrow-up5arrow-down1·6 hours agoAt 3 tokens a second and calling it useble I would guess? I see people claiming that shit all the time and it’s baffling.
minus-squarejaschen306@sh.itjust.workslinkfedilinkEnglisharrow-up1·52 minutes agohttps://sh.itjust.works/comment/28041846 I didn’t believed it until I started using it.
minus-squarechrisashtear@lemmy.ziplinkfedilinkEnglisharrow-up3arrow-down1·6 hours agoThey said 50- i looked up strata, and it uses smaller quantizations/optimizations of that model depending on your system. I have 48g vram and 192g system ram and get ~15t/s on qwen 3.8 flash next at Q4. Off the top of my head. I think Q6 is 12.
minus-squarejaschen306@sh.itjust.workslinkfedilinkEnglisharrow-up1·53 minutes agohttps://sh.itjust.works/comment/28041846 Try it out and let me know if you can get higher.
How do you run qwen 3.8 flash next on 16gb vram, if you don’t mind me asking ?
https://github.com/niko1221/strata
The model I’m using is a Q4. Unsloth UD-IQ4_XS
At 3 tokens a second and calling it useble I would guess?
I see people claiming that shit all the time and it’s baffling.
https://sh.itjust.works/comment/28041846
I didn’t believed it until I started using it.
They said 50- i looked up strata, and it uses smaller quantizations/optimizations of that model depending on your system.
I have 48g vram and 192g system ram and get ~15t/s on qwen 3.8 flash next at Q4. Off the top of my head. I think Q6 is 12.
https://sh.itjust.works/comment/28041846
Try it out and let me know if you can get higher.