Are you sure about that? High memory speed is great for dense models, or when serving at high concurrency.
However for local single-user setups, it's often better to have access to more capable/bigger MoE models at reasonable speeds and lower concurrences, which is enabled by these platforms.
If you're using a MoE model, then why do you care about the larger RAM offered by these devices? That's the main problem with low bandwidth devices: they limit the effective ram you can make use.
I do (and have historically done) quite a work with both local LLMs and local diffusion models. I have an M3 Max MBP at 400 GB/s and also a desktop with a RTX 4090 with 1,008 GB/s
While the M3 Max MBP can serve up MoE reasonably fast (~60 token/sec)the RTX 4090 is an entirely different experience (~170 token/sec). I also do a fair bit of experimentation and am currently running a custom decoder that requires expensive look-ahead, but I'm still able to get a usable 25 token/s on the RTX.
The raison d'etre for the DGX spark is not practical home inference, but rather offering the same fundamental architecture as data center cards for a affordable CUDA prototyping. If you want to build software to run on H100s, you probably can't justify buying (and running) a single card. The DGX spark solves this by having the same fundamental setup as what those cards have.
That makes these non-NVIDIA DGX-like devices confusing to me. The entire benefit of the DGX series is the NVIDIA architecture itself.
Anyone interested in home LLMs should decide whether a Mac or a dedicated GPU is the more sensible path based on their budget and other computer use. Each has their own benefits.
I run DSv4 Flash at home on 2 DGX Sparks and am pretty sure there is no more cost effective way for me to do so. I'm not interested in running smaller models.
Using regular DeepSeek-V4-Flash, I see 2000tok/s prompt processing and from 40 to 50 tok/s generation. Performance doesn't drop much at long contexts, DSv4 is really nice for that.
With DeepSeek-V4-Flash-DSpark (Deepseek's new speculative decoding scheme), which is still barely supported anywhere, we're seeing a more steady 45-55 tok/s with bursts into the 60s.
What quant size are you using? Just picked up my second spark and a cable and wanted to try this one out for fun. I generally run a bunch of models for different purposes (easy / bulk tasks) and use APIs for harder tasks.
However for local single-user setups, it's often better to have access to more capable/bigger MoE models at reasonable speeds and lower concurrences, which is enabled by these platforms.