| ▲ | wmf 2 hours ago | |
That just sounds like a 3090. | ||
| ▲ | cyanydeez 15 minutes ago | parent [-] | |
not at the vram sizes that control how much context to load; also, GPUs arn't as effiecient as direct inference. | ||
| ▲ | wmf 2 hours ago | |
That just sounds like a 3090. | ||
| ▲ | cyanydeez 15 minutes ago | parent [-] | |
not at the vram sizes that control how much context to load; also, GPUs arn't as effiecient as direct inference. | ||