That's not what parent said, but this is already quite decent speed for unattended inference (overnight or even spanning multiple business days) which is arguably the right target for this model. This is a challenging model to infer locally, it has roughly ~115 GB of dense active parameters(!) plus ~25 GB of sparsely routed experts per token. Plus the KV cache (which is actually reasonably lean for this one model, around 27GB for a full 1Mtok context). What you're seeing in antirez's video is essentially the performance we should expect from a 128GiB system that has to load sparsely routed experts in full from disk because there's no real room for caching them.
192GiB Gorgon Halo systems will be an interesting future target for this model, the best you can do with 128GiB or less is probably to push batching higher in order to amortize the weights traffic over multiple inferences - which of course will sink single-session speeds even lower for a modest gain in total throughput.
No one will ever derive any utility from running models at this speed. Please prove me wrong. Give me the number of tokens input and output (and dont forget about reasoning) and acceptable time to wait for it and the use case.
antirez's own video (the one I referenced in my comment) shows K3 inference running on M5 Max, not M1-series silicon (which is OP). M1 series has far lower SSD read throughput and memory bandwidth, and can barely fit the model weights on its maxed out internal storage (2TB). (This is why the linked OP resorts to streaming the sparse parameters from the network which is incredibly slow.)
My answer doesn't change if it is M5s. Where is the math showing a 98% discount over K3 on openrouter. Heck, where is the math showing it is any % cheaper? How much electricity will your M5 sip to hit 1M input and 1M output tokens that would cost $3 + $15 there? I bet it is more expensive on the Mac.
192GiB Gorgon Halo systems will be an interesting future target for this model, the best you can do with 128GiB or less is probably to push batching higher in order to amortize the weights traffic over multiple inferences - which of course will sink single-session speeds even lower for a modest gain in total throughput.