Category Archives: Hardware

Apple, Hardware

Yet another Mac Studio M3 Ultra this time with 512GB

Did I say enough…..
meh….

Okay lesson learned, never enough.
My “1 month old” M3 Ultra 256GB went out of memory running all those models and podman containers in parallel.



My current setup is:
OpenWebUI:
-> LM Studio, Aya-Vision-32b,
-> ComfyUI workflow with t5xxl, Flux1.dev, llama-3.1
-> MCP proxified: Searxng, wikipedia, docling, context7, time, memory, weather, sequential-thinking
Podman: 24 containers including supabase, wikijs, watchtower…

Also I discovered that I can use OpenWebUI, SwarmUI, exo and even mlx
to distribute workload across both Mac Studios via 80GBs thunderbolt 5 bridging.

And with the orange clown, you never know if there will be a new M4 Ultra next year at all.

Apple, Hardware

Upgraded my old M1 mini to Mac Studio M3 Ultra 256GB

Finally the latest Mac Studio was released, unfortunately only with M3 chip instead of a M4, but I simply waited too long already.
Let’s see how this one compares to the previous M4 Pro I bought for my son in regards to LLM’s.

This one will be used with Podman Desktop, LM Studio and hopefully be fast enough to also handle voice recognition and rendering in realtime.

256GB VRAM will be more than enough for my use cases, 96GB was simply not enough as I already saw that on the 64GB M4.

Apple, Hardware

M4 Pro mini for my son

Time to pass along one of my old M1 minis to my parents, and get a newer M4 Pro for my son, and of course further LLM testing.

So I decided to get the maximum configuration with 64GB and the pro version with highest frequency and core count.

Not sure if it will be sufficient for video rendering in ComfyUI as well, let’s see.
Overall I expect a 4 times faster speed for across all scenarios.

Hardware

AMD Ryzen 9 5900XT

The final upgrade for my old X570 AMD platform.
Since I already upgraded to an Nvidia, and LLM power is still not enough, I now try a 32 threads CPU. (low power of course)

I also invested first time in a closed system water cooling from Arctic Liquid Freezer III 360.

And I also updated RAM to max 128GB.

This is the end for that Taichi X570 motherboard, probably a goodbye to the PC platform finally, as Apple can now even cleanly emulate DirectX in Metal.


And already the LLM knows what’s best for me 😀

no need to write 5000 words, I can do it in less 😀 damn poser LLM

Hardware

Palit GeForce RTX 4080 GamingPro 16GB

Just bought a Nvidia 4080 as the ROCm bullshit on AMD is really driving me crazy. Every machine learning software I try has issues when using ONNX or other openCL capabilities, and also VRAm is always an issue even with my old and fast Sapphire Radeon RX 5700 XT 8GB.

Sorry AMD, I did like your power efficiency, but your software skills are just horrible.