I may or may not have splurged on a 128GB AMD Ryzen AI Max 395 (strix halo) system for ‘AI stuff’ (told you I was a noob).

I’ve been running Ubuntu on it with the AMD drivers (think its ROCm?), ollama and seems to be working fine.

An LLM told me to change the RAM/VRAM ratio to 50:50 (so 64GB for the CPU, 64GB for the GPU). I dunno if that was correct, seems like a waste tbh. Feels like I could give the GPU more resources and run bigger models.

I’ve read about Lemonade being better than Ollama on strix halo? Also, I realised that I might not be using the NPU as extra work is required to get that up and running.

I’m looking for advice from users on the same hardware. What OS are you using? How do you have the RAM/VRAM ratio configured? What’s your stack? That sorta thing.

PS - If my wife asks, the machine only cost like £250 and is a second-hand floor model.

  • SirDimples@programming.devEnglish
    0·
    6 days ago

    You don’t need to worry about the split in strix halo, it runs a unified memory architecture so Linux will dynamically allocate VRAM on demand up to maximum possible (which would be around 120GB I think)

    I’m on an nvidia system so can’t answer the rest of your questions other than to say that in my experience ollama gave me a much worse tokens per second speed compared to running the same model using llama.cpp, so if you get something slower than you expect it might be ollama caused.

    Good luck with your £250 system 😉

    • Luminous5481 "Enemy of the State"@anarchist.nexusEnglish
      0·
      6 days ago

      that being said, most apps won’t recognize the unified memory because because the Strix Halo is so new, so if you want accurate reporting of GPU usage, you have to set a specific amount. otherwise it will probably report 100% usage of 512M VRAM in apps like btop.

    • jobbies@lemmy.zipOPEnglish
      0·
      6 days ago

      You don’t need to worry about the split in strix halo, it runs a unified memory architecture so Linux will dynamically allocate VRAM on demand up to maximum possible

      That’s what I assumed it would do. Tried running an 80gb model and it barfed saying it was ‘out of memory’. The LLM I consulted said it was because it needs to load the model into system RAM first then pass it to VRAM (It was set at the default 96GB RAM/32GB VRAM).

      Good luck with your £250 system 😉

      I know. Bargain, right? 🥴