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.
I have a 3090, 7800, and 128GB frame 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.
I have a 3090, 7800, and 128GB frame 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…