|
|
|
|
|
|
by zozbot234
84 days ago
|
|
|
M3 has tolerable decode performance for the price, and that's what people would care about most of the time. they underperform severely wrt. prefill, but that's a fraction of the workload. AI, even agentic AI, spends most of its time outputing tokens, not processing context in bulk. |
|
|