logoalt Hacker News

kilroy123yesterday at 2:32 PM3 repliesview on HN

I hope to see something like this, but in a small form factor like the NVIDIA spark.

I want a super fast LLM that is Opus 4.6+, like, in ability.


Replies

wmfyesterday at 4:26 PM

Memory bandwidth is the bottleneck in the Spark. If you replace the SoC with an optimized ASIC but keep the same 256-bit LPDDR5 the performance will be the same. You can increase performance by using wider memory but that's also more expensive.

show 1 reply
smith7018yesterday at 4:57 PM

Unfortunately Sam Altman won't be the one to deliver us at-home hardware that can run Opus-level models

show 1 reply
flyinglizardyesterday at 5:44 PM

Forget about it. Datacenter class hardware is getting farther and farther from desktop use. It’s not PCIe GPUs anymore.