- 21comments
- 407comments
- 11comments
- 209comments
- 199comments
- 116comments
- 274comments
- 40comments
- 273comments
- 192comments
- 20comments
- —discuss
- 78comments
- 38comments
- 7comments
- 5comments
- 271comments
- 2comments
- —discuss
- 159comments
- 7comments
- 50comments
- 141comments
- 2comments
- 416comments
- 170comments
- 5comments
- 439comments
- 58comments
- 131comments
Stupid metric. It's not because a model is better performing that it necessarily requires more energy or compute.
I don't think that's what they are saying. In fact if they did the metric would be pointless. Rather they are saying by estimating that value on different architectures, one can find more efficient ones. They use open model to be able to remove unknowns. They aren't advocating for one model or another, only more efficient architectures.
Stupid metric. It‘s not because you spend more time that you travel farther.
s/
Unless I misread it, are they saying local GPUs use less energy?
That’s surprising, almost unbelievable, due to batching. Local is usually not batched.
Small models are much smaller than frontier models though, which is how they end up consuming less energy despite low batch count. (Though with local models growing strong agentic capabilities, batching becomes a reality with local models as well).