|
|
|
|
|
|
by moffkalast
813 days ago
|
|
|
Well consumer hardware can run something in the order of ~50B quantized at a "reasonable" price today, we'd need about 5 or 6 doublings to run something that would be GPT 4 tier at 1T+. So, it would need to continue for roughly a decade at least? Current models are horrendously inefficient though, so with architectural improvements we'll have something of that capability far sooner on weaker hardware. |
|
|