themachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 23 days 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-square118fedilinkarrow-up1443arrow-down18 cross-posted to: [email protected][email protected]
arrow-up1435arrow-down1external-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 · 23 days agomessage-square118fedilink cross-posted to: [email protected][email protected]
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up2·edit-223 days 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-up0arrow-down1·22 days agoA used 3090 alone is like what, 4-5k now? Your setup isn’t really achievable for most now.
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.