themachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 16 hours agoScientist says RAM pricing has risen to normalized 2007 levels, AI shortage undid 20 years of progress in a matter of months — memory prices had been falling exponentially for decadeswww.tomshardware.comexternal-linkmessage-square59fedilinkarrow-up1297 cross-posted to: technology@lemmy.mltechnology@beehaw.orgpcmasterrace@lemmy.worldtechnology@midwest.social
arrow-up1297external-linkScientist says RAM pricing has risen to normalized 2007 levels, AI shortage undid 20 years of progress in a matter of months — memory prices had been falling exponentially for decadeswww.tomshardware.comthemachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 16 hours agomessage-square59fedilink cross-posted to: technology@lemmy.mltechnology@beehaw.orgpcmasterrace@lemmy.worldtechnology@midwest.social
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up3·edit-210 hours ago which I think is only available from China right now. Nah, 0731 weights were released. I’m running it locally right this second. I don’t know about Deepseek API specifically, but there are tons of places to get it.
minus-squarejaschen306@sh.itjust.workslinkfedilinkEnglisharrow-up1·6 hours agoYou are Mr. moneybags or you’re running 2 or 4bit quantized.
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up2·edit-24 hours agoI have a 3090, 7800, and 128GB ram from pre-rampocalypse. It’s not nothing, but there are definitely crazier home labs. Deepseek V4 is native 4 bit. I am running this quant, but the quantization loss is measurably low: https://huggingface.co/Downtown-Case/DeepSeek-V4-Flash-0731-128GB-RAM-IK-GGUF The native MXFP4 is only a bit bigger.
minus-squareboonhet@sopuli.xyzlinkfedilinkEnglisharrow-up1·45 minutes agoA used 3090 alone is like what, 4-5k now? Your setup isn’t really achievable for most now.
Nah, 0731 weights were released. I’m running it locally right this second.
I don’t know about Deepseek API specifically, but there are tons of places to get it.
You are Mr. moneybags or you’re running 2 or 4bit quantized.
I have a 3090, 7800, and 128GB ram from pre-rampocalypse. It’s not nothing, but there are definitely crazier home labs.
Deepseek V4 is native 4 bit.
I am running this quant, but the quantization loss is measurably low: https://huggingface.co/Downtown-Case/DeepSeek-V4-Flash-0731-128GB-RAM-IK-GGUF
The native MXFP4 is only a bit bigger.
A used 3090 alone is like what, 4-5k now?
Your setup isn’t really achievable for most now.