Post #4509991
2026-08-09 00:39 UTC
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: huggingface.co/…/DeepSeek-V4-Flash-0731-128GB-RAM…
The native MXFP4 is only a bit bigger.
Replies (1)
-
@boonhet@sopuli.xyz 2026-08-09 06:13
A used 3090 alone is like what, 4-5k now? Your setup isn’t really achievable for most now.