This will crush the M5 Max going by the numbers. I'm curious to see how much they end up costing

Tiberium 15 hours ago | parent | next [-]

It won't, the top tier RTX Spark has the same exact CPU and GPU as DGX Spark, so you can check DGX Spark CPU benchmarks to see how it fares. Spoiler: it's about M3 Max level. And they're only coming this fall.

▲

aenis 15 hours ago | parent | prev | next [-]

Nah, still ~300GB/s memory bandwidth. That will be slower than the M5 max, by a wide margin for LLM inference.

▲

Rekindle8090 15 hours ago | parent | prev [-]

M5 max is 3x stronger and 50% more power efficient. nice try though.

▲

spwa4 12 hours ago | parent [-]

... but you'll be rewriting inference for any model that isn't a well-known LLM. Yourself.

	▲	wbolt 5 hours ago \| parent [-]
		AI coding agents can do that pretty nicely already and it will only (slowly) improve over time.