1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
jeffgeerling.com
1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
1–10 of 236 posts
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#2My expectations from M5 Max/Ultra devices:
- Something like DGX QSFP link (200Gb/s, 400Gb/s) instead of TB5. Otherwise, the economies of this RDMA setup, while impressive, don't make sense.
- Neural accelerators to get prompt prefill time down. I don't expect RTX 6000 Pro speeds, but something like 3090/4090 would be nice.
- 1TB of unified memory in the maxed out version of Mac Studio. I'd rather invest in more RAM than more devices (centralized will always be faster than distributed).
- +1TB/s bandwidth. For the past 3 generations, the speed has been 800GB/s...
- The ability to overclock the system? I know it probably will never happen, but my expectation of Mac Studio is not the same as a laptop, and I'm TOTALLY okay with it consuming +600W energy. Currently it's capped at ~250W.
Also, as the OP noted, this setup can support up to 4 Mac devices because each Mac must be connected to every other Mac!! All the more reason for Apple to invest in something like QSFP.
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#3> Working with some of these huge models, I can see how AI has some use, especially if it's under my own local control. But it'll be a long time before I put much trust in what I get out of it—I treat it like I do Wikipedia. Maybe good for a jumping-off point, but don't ever let AI replace your ability to think critically!
It is a little sad that they gave someone an uber machine and this was the best he could come up with.
Question answering is interesting but not the most interesting thing one can do, especially with a home rig.
The realm of the possible
Video generation: CogVideoX at full resolution, longer clips
Mochi or Hunyuan Video with extended duration
Image generation at scale:
FLUX batch generation — 50 images simultaneously
Fine-tuning:
Actually train something — show LoRA on a 400B model, or full fine-tuning on a 70B
but I suppose "You have it for the weekend" means chatbot go brrrrr and snark
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#4My expectations from M5 Max/Ultra devices: - Something like DGX QSFP link (200Gb/s, 400Gb/s) instead of TB5. Otherwise, the economies of this RDMA setup, while impressive, don't make sense. - Neural accelerators to get prompt prefill time down. I don't expect RTX 6000 Pro speeds, but something like 3090/4090 would be nice. - 1TB of unified memory in the maxed out version of Mac Studio. I'd rather invest in more RAM t…
> TOTALLY okay with it consuming +600W energy
The 2019 i9 Macbook Pro has entered the chat.
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#5https://m.youtube.com/watch?v=4l4UWZGxvoc
Seems like the ecosystem is rapidly evolving
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#6> Working with some of these huge models, I can see how AI has some use, especially if it's under my own local control. But it'll be a long time before I put much trust in what I get out of it—I treat it like I do Wikipedia. Maybe good for a jumping-off point, but don't ever let AI replace your ability to think critically! It is a little sad that they gave someone an uber machine and this was the best he could come u…
Yea, I don't understand why people use LLMs for "facts". You can get them from Wikipedia or a book.
Use them for something creative, write a short story on spec, generate images.
Or the best option: give it tools and let it actually DO something like "read my message history with my wife, find top 5 gift ideas she might have hinted at and search for options to purchase them" - perfect for a local model, there's no way in hell I'd feed my messages to a public LLM, but the one sitting next to me that I can turn off the second it twitches the wrong way? - sure.
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#7Hey Jeff, wherever you are: this is awesome work! I’ve wanted to try something like this for a while and was very excited for the RDMA over thunderbolt news.
But I mostly want to say thanks for everything you do. Your good vibes are deeply appreciated and you are an inspiration.
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#8The largest nodes in his cluster each have 512GB RAM. DeepSeek V3.1 is a 671B parameter model whose weights take up 700GB RAM: https://huggingface.co/deepseek-ai/DeepSeek-V3.1
I would have expected that going from one node (which can't hold the weights in RAM) to two nodes would have increased inference speed by more than the measured 32% (21.1t/s -> 27.8t/s).
With no constraint on RAM (4 nodes) the inference speed is less than 50% faster than with only 512GB.
Am I missing something?
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#9My expectations from M5 Max/Ultra devices: - Something like DGX QSFP link (200Gb/s, 400Gb/s) instead of TB5. Otherwise, the economies of this RDMA setup, while impressive, don't make sense. - Neural accelerators to get prompt prefill time down. I don't expect RTX 6000 Pro speeds, but something like 3090/4090 would be nice. - 1TB of unified memory in the maxed out version of Mac Studio. I'd rather invest in more RAM t…
Apple has always sucked at properly embracing properly robust tech for high-end gear for markets outside of individual prosumer or creatives. When Xserves existed, they used commodity IDE drives without HA or replaceable PSUs that couldn't compete with contemporary enterprise servers (HP-Compaq/Dell/IBM/Fujitsu). Xserve RAID interconnection half-heartedly used fiber channel but couldn't touch a NetApp or EMC SAN/filer. I'm disappointed Apple has a persistent blindspot preventing them from succeeding in data center-quality gear category when they could've had virtualized servers, networking, and storage, things that would eventually find their way into my home lab after 5-7 years.
Re: 1.5 TB of VRAM on Mac Studio – RDMA over Thunderbolt 5
#10The largest nodes in his cluster each have 512GB RAM. DeepSeek V3.1 is a 671B parameter model whose weights take up 700GB RAM: https://huggingface.co/deepseek-ai/DeepSeek-V3.1 I would have expected that going from one node (which can't hold the weights in RAM) to two nodes would have increased inference speed by more than the measured 32% (21.1t/s -> 27.8t/s). With no constraint on RAM (4 nodes) the inference speed i…
the TB5 link (RDMA) is much slower than direct access to system memory