- Популярные видео
- Авто
- Видео-блоги
- ДТП, аварии
- Для маленьких
- Еда, напитки
- Животные
- Закон и право
- Знаменитости
- Игры
- Искусство
- Комедии
- Красота, мода
- Кулинария, рецепты
- Люди
- Мото
- Музыка
- Мультфильмы
- Наука, технологии
- Новости
- Образование
- Политика
- Праздники
- Приколы
- Природа
- Происшествия
- Путешествия
- Развлечения
- Ржач
- Семья
- Сериалы
- Спорт
- Стиль жизни
- ТВ передачи
- Танцы
- Технологии
- Товары
- Ужасы
- Фильмы
- Шоу-бизнес
- Юмор
Build Your Own AI server
I built a DIY AI server to see how far a home setup can go without a DGX or a pricey custom workstation. This video covers the options, the parts I chose (and why), and real benchmarks across LLMs, image generation, and ML training.
Chapters (timestamps):
00:00 Intro
00:54 AI server options
01:29 Parts: Motherboard
02:24 Parts: CPU
02:48 Parts: RAM
02:56 Parts: Cooling
03:18 Parts: PSU
03:28 Parts: GPU
04:33 LLM Benchmarks: gpt‑oss 20B (parallel)
06:04 LLM Benchmarks: gpt‑oss 20B (single‑request)
07:28 LLM Benchmarks: gpt‑oss 120B (sharded)
08:20 Image Gen Benchmarks: FLUX.1 dev
09:48 ML Training Benchmarks: ResNet50
11:19 Cost comparison
12:09 Wrap‑up & plans
14:18 Extra stuff / credits
Corrections:
08:22 FLUX.1 isn’t a Stable Diffusion model but it’s a transformer-based, rectified-flow diffusion model.
10:18 not a GPU, but this is Nvidia's Grace CPU. Wrong image.
Related Videos:
https://youtu.be/AL7C5yCx6FM
Deep Dives with Christina — https://youtu.be/SeXXQ-HLU2I
Ways to support:
Subscribe -- https://www.youtube.com/c/JunYamog?sub_confirmation=1
Videos Mentioned:
@theNittyGritty — Why I am not gonna buy the NVIDIA DGX Spark https://youtu.be/R197j4x82SM?si=I4gP83lSoigvi7Db
@DigitalSpaceport — INSANE Home AI Server - Quad 3090 Build https://youtu.be/JN4EhaM7vyw?si=j5ADHOjQW_ztqmIS
References:
gpt-oss - https://openai.com/index/introducing-gpt-oss/
vLLM - https://docs.vllm.ai/en/latest/
llama.cpp - https://github.com/ggml-org/llama.cpp
nVidia GenAI-Perf - https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/perf_benchmark/genai_perf.html
Apple MLX - https://opensource.apple.com/projects/mlx/
ML Training ResNet50 (forked from M Bourke's benchmarks and added torch discributed for multi GPU runs) - https://github.com/jkyamog/mac-ml-speed-test/blob/main/pytorch_test_computer_vision_cifar100.py
If you’d rather buy than build, check out Bizon Tech (not sponsored) — https://bizon-tech.com/deep-learning-ai-workstation
Motion 5 animations by Simple Video Making (not sponsored) — https://simplevideomaking.com/
Видео Build Your Own AI server канала Jun Yamog
Chapters (timestamps):
00:00 Intro
00:54 AI server options
01:29 Parts: Motherboard
02:24 Parts: CPU
02:48 Parts: RAM
02:56 Parts: Cooling
03:18 Parts: PSU
03:28 Parts: GPU
04:33 LLM Benchmarks: gpt‑oss 20B (parallel)
06:04 LLM Benchmarks: gpt‑oss 20B (single‑request)
07:28 LLM Benchmarks: gpt‑oss 120B (sharded)
08:20 Image Gen Benchmarks: FLUX.1 dev
09:48 ML Training Benchmarks: ResNet50
11:19 Cost comparison
12:09 Wrap‑up & plans
14:18 Extra stuff / credits
Corrections:
08:22 FLUX.1 isn’t a Stable Diffusion model but it’s a transformer-based, rectified-flow diffusion model.
10:18 not a GPU, but this is Nvidia's Grace CPU. Wrong image.
Related Videos:
https://youtu.be/AL7C5yCx6FM
Deep Dives with Christina — https://youtu.be/SeXXQ-HLU2I
Ways to support:
Subscribe -- https://www.youtube.com/c/JunYamog?sub_confirmation=1
Videos Mentioned:
@theNittyGritty — Why I am not gonna buy the NVIDIA DGX Spark https://youtu.be/R197j4x82SM?si=I4gP83lSoigvi7Db
@DigitalSpaceport — INSANE Home AI Server - Quad 3090 Build https://youtu.be/JN4EhaM7vyw?si=j5ADHOjQW_ztqmIS
References:
gpt-oss - https://openai.com/index/introducing-gpt-oss/
vLLM - https://docs.vllm.ai/en/latest/
llama.cpp - https://github.com/ggml-org/llama.cpp
nVidia GenAI-Perf - https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/perf_benchmark/genai_perf.html
Apple MLX - https://opensource.apple.com/projects/mlx/
ML Training ResNet50 (forked from M Bourke's benchmarks and added torch discributed for multi GPU runs) - https://github.com/jkyamog/mac-ml-speed-test/blob/main/pytorch_test_computer_vision_cifar100.py
If you’d rather buy than build, check out Bizon Tech (not sponsored) — https://bizon-tech.com/deep-learning-ai-workstation
Motion 5 animations by Simple Video Making (not sponsored) — https://simplevideomaking.com/
Видео Build Your Own AI server канала Jun Yamog
DIY AI server home lab AI server AI workstation build multi GPU build NVIDIA A100 RTX 5080 OCuLink vLLM llama.cpp Apple MLX gpt-oss 20B gpt-oss 120B Flux Dev GenAI perf tensor parallel model sharding cost comparison DGX Station DGX Spark ProArt Z890 LLM Benchmarks Stable Diffusion AI Benchmarks AI server RTX 3090 Noctua GPU AI home build gpt-oss M4 Max Local AI DGX nvidia jetson jetson thor
Комментарии отсутствуют
Информация о видео
27 августа 2025 г. 3:17:23
00:14:59
Другие видео канала




