s_mcleod, 8 months ago M.2 NVMe -> PCIe x16 + some dodgy cabling = Tesla P100 eGPU 😂 Combined with my RTX3090 I can load Q4/Q5 70b models 100% into vRAM with exllama or autogpqt #LLM #AI #ML #Llama #Nvidia #GPT image/png image/jpeg image/png
M.2 NVMe -> PCIe x16 + some dodgy cabling = Tesla P100 eGPU 😂
Combined with my RTX3090 I can load Q4/Q5 70b models 100% into vRAM with exllama or autogpqt
#LLM #AI #ML #Llama #Nvidia #GPT
image/png image/jpeg image/png