Search results

  1. D

    Build for 24/7 local LLM for inference with 2 separate GPUs

    I want to build a headless compute machine to run a RTX Ada 4000 (20GB) with a RTX Pro 5000 (48GB) or RTX PRO 4500 (32GB) in parallel for inference. The goal is not running one large model using 2x GPUs, but rather running separate models on each GPU. Why these GPU config? because I already had...
  2. D

    Ideas needed for a Low Power system around DDR4 ECC RDIMM

    These are It’s a i350 NIC. No 10Gb gadget yet.
  3. D

    Ideas needed for a Low Power system around DDR4 ECC RDIMM

    I already have the RAMs (16x 16GB DDR4 ECC RDIMM, quite overkill I know), they are in my dual Xeon E5 2630L v3 machine which is now low power and is now offline since a while ago! It eats 80-100W in idle mode. I want to swap the CPU and motherboard only. The rest of the system is in place...
  4. D

    Ideas needed for a Low Power system around DDR4 ECC RDIMM

    What would be a low power and affordable build for a home server with DDR4 ECC RDIMM RAM modules? It looks like most CPUs need UDIMM. Is there any low power CPU, with rather low TDP and low idle power usage that can work with RDIMM ?
  5. D

    Fujitsu TX1320 M3 - Cheap low power server (barebone)

    Does this TX1320 M3 require only UDIMM or can it work with RDIMM too?
Top Bottom