← Back to context Comment by officerk 13 hours ago This will crush the M5 Max going by the numbers. I'm curious to see how much they end up costing 5 comments officerk Reply Tiberium 13 hours ago 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 13 hours ago Nah, still ~300GB/s memory bandwidth. That will be slower than the M5 max, by a wide margin for LLM inference. Rekindle8090 13 hours ago M5 max is 3x stronger and 50% more power efficient. nice try though. spwa4 10 hours ago ... but you'll be rewriting inference for any model that isn't a well-known LLM. Yourself. wbolt 3 hours ago AI coding agents can do that pretty nicely already and it will only (slowly) improve over time.
Tiberium 13 hours ago 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 13 hours ago Nah, still ~300GB/s memory bandwidth. That will be slower than the M5 max, by a wide margin for LLM inference.
Rekindle8090 13 hours ago M5 max is 3x stronger and 50% more power efficient. nice try though. spwa4 10 hours ago ... but you'll be rewriting inference for any model that isn't a well-known LLM. Yourself. wbolt 3 hours ago AI coding agents can do that pretty nicely already and it will only (slowly) improve over time.
spwa4 10 hours ago ... but you'll be rewriting inference for any model that isn't a well-known LLM. Yourself. wbolt 3 hours ago AI coding agents can do that pretty nicely already and it will only (slowly) improve over time.
wbolt 3 hours ago AI coding agents can do that pretty nicely already and it will only (slowly) improve over time.
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.
Nah, still ~300GB/s memory bandwidth. That will be slower than the M5 max, by a wide margin for LLM inference.
M5 max is 3x stronger and 50% more power efficient. nice try though.
... but you'll be rewriting inference for any model that isn't a well-known LLM. Yourself.
AI coding agents can do that pretty nicely already and it will only (slowly) improve over time.