The Q4 quantization requires about 600GB of RAM without context, not exactly consumer hardware friendly.
Has Kimi found a way to vastly reduce the amount of VRAM required without running at 3 tokens per second? That’s the real concern.
I said "open weight" rather than "local". I mean, local if you have $240k to drop on GPUs but you can run Kimi k2.6 on a B300 cluster for ~$50/hour too.