AI Hardware Writeup https://digitalspaceport.com/homelab-ai-server-rig-tips-tricks-gotchas-and-takeaways
GPUs mentioned
4090 https://geni.us/4090_24GB_GPU
3090 https://geni.us/GPU3090
3060 https://geni.us/3060_GPU_12GB
P2000 https://geni.us/Quadro_P2000
K2200 https://geni.us/K2200_GPU
MOBOs mentioned
H12-ssl-i https://geni.us/MBD_H12SSL-I-O
MZ32-AR0 https://geni.us/mz32-ar0_motherboard
AsRock wrx80 https://geni.us/ASRock_wrx80_creator
CPUs mentioned
EPYC 7F52 https://geni.us/EPYC_7F52_UpvU
EPYC 7702 https://geni.us/EPYC_7702
Threadripper 5955wx https://geni.us/ThreadripperPRO_5955wx
Storage
Samsung 990 PRO https://geni.us/Samsung_990_PRO
Samsung 980 PRO https://geni.us/Samsung_980_PRO
Samsung EVO 870 1TB or 2TB https://geni.us/870_EVO_2TB
LOCAL AI SERVER BUILD WRITEUPS
Super Low Budget Ai Server https://digitalspaceport.com/local-ai-home-server-at-super-low-150-budget-price/
Low Budget Ai Server https://digitalspaceport.com/local-ai-home-server-at-low-350-budget-price/
Mid Range Ai Server https://digitalspaceport.com/local-ai-home-server-build-at-mid-range-750-price/
High End AI Server https://digitalspaceport.com/local-ai-home-server-build-at-high-end-5000-price/
QUAD 3090 AI HOME SERVER BUILD https://youtu.be/JN4EhaM7vyw
GPU Rack Frame https://geni.us/GPU_Rack_Frame
Supermicro H12ssl-i MOBO (better option vs mz32-ar0) https://geni.us/MBD_H12SSL-I-O
Gigabyte MZ32-AR0 MOBO https://geni.us/mz32-ar0_motherboard
AMD 7V13 (newer, faster vs 7702) https://geni.us/EPYC_7V13_CPU
RTX 3090 24GB GPU (x4) https://geni.us/GPU3090
256GB (8x32GB) DDR4 2400 RAM https://geni.us/256GB_DDR4_RAM
PCIe4 Risers (x4) https://geni.us/PCIe4_Riser_Cable
AMD SP3 Air Cooler (easier vs water cooler) https://geni.us/EPYC_SP3_COOLER
iCUE H170i water cooler https://geni.us/iCUE_H170i_Capellix
(sTRX4 fits SP3 and retention kit comes with the CAPELLIX)
CORSAIR HX1500i PSU https://geni.us/Corsair_HX1500iPSU
4i SFF-8654 to 4i SFF-8654 (x4, not needed for H12SSL-i) https://geni.us/SFF8654_to_SFF8654
ARCTIC MX4 Thermal Paste https://geni.us/Arctic_ThermalPaste
Kritical Thermal GPU Pads https://geni.us/Kritical-Thermal-Pads
HDD Rack Screws for Fans https://geni.us/HDD_RackScrews
24GB AI SERVER BUILD https://youtu.be/3XC8BA5UNBs
HP Z440 https://geni.us/HP_Z440
3060 12GB (need 2 for 24GB) https://geni.us/3060_GPU_12GB
6 to 8 pin PCIe adapter cable https://geni.us/GPUPowerAdapt6pin-8pin
BUDGET 12GB AI SERVER https://youtu.be/iflTQFn0jx4
Dell Precision 3620 Tower https://geni.us/Precision_3620
3060 12GB GPU https://geni.us/3060_GPU_12GB
GPU 6 to 8 pin Power Adapter https://geni.us/GPUPowerAdapt6pin-8pin
SUPER BUDGET 4GB AI SERVER https://youtu.be/VV30CMHc-kY
Dell Optiplex 7050 MT https://geni.us/OptiPlex7050MT
Quadro K2200 GPU (x2) https://geni.us/K2200_GPU
Be sure to 👍✅Subscribe✅👍 for more content like this!
Join this channel https://www.youtube.com/@DigitalSpaceport/join
Digital Spaceport Website https://digitalspaceport.com
Patreon https://www.patreon.com/digitalspaceport
Buy Me a Coffee https://buymeacoffee.com/digitalspaceport
Please share this video to help spread the word and drop a comment below with your thoughts or questions. Thanks for watching!
Chapters
0:00 Ai Home Server Hardware
0:45 GPUs for Ai Tips and Tricks
2:06 How Many GPUs for ai server
3:34 Does 2 GPUs speed up inference speed?
4:58 Always on Home Ai
6:29 Other reasons for multi GPUs
7:11 Apple M4 MAX vs CUDA
8:49 PSUs for Ai
10:00 RAM speed for LLMs
10:45 CPU Thread speed impact on tokens per second
12:10 CPU for Ai Server
13:50 EPYC Rome CPU for Ai
14:12 EPYC Mobo tips and tricks
17:05 $150 Home Ai Server Rig
17:45 $350 Ai Vision Server Llama 3.2
19:29 24GB GPU Rigs start at 1K
21:13 Quad 3090 Ai Rig
22:03 Buyer tips on eBay
23:14 Cheap K2200 Ai GPU
24:14 GPU Frame Rig Lessons Learned
*****
As an Amazon Associate I earn from qualifying purchases.
When you click on links to various merchants on this site and make a purchase, this can result in this site earning a commission. Affiliate programs and affiliations include, but are not limited to, the eBay Partner Network.
*****