Rumored Local Benchmarks for Kimi K3
Stefania_druga · x · 2026-07-18
The repost speculates on the local deployment requirements for Kimi K3: based on rumored parameter counts, it might take 4 512GB M3 Ultra Mac Studios to run, totaling around 2TB of memory, paired with MTP + Tensor Parallelism and utilizing RDMA over Thunderbolt 5 for parallel processing.
The original post also mentions that once the weights are available, the author will release full benchmarks on their local platform. Currently, based on rumor-based estimates, they believe it could achieve 30+ tok/s locally, with slower forward prefilling. However, if a 512GB M5 Ultra is released in the future, prefill speeds could increase by roughly 5x.
More from Infra
- Cloud capacity crisis is now an AI architecture problem, argues new newsletter — DavidLinthicum · 2026-10-26
- SpaceX files $40B GPU financing commitment with Apollo, already at 1.7GW — XFreeze · 2026-10-26
- Meta plans to raise up to $95B to fund massive AI expansion — Polymarket · 2026-10-26
- Nebius CEO: Debt Markets Closed for Neoclouds Last Week, Leaning on Customer Advances — zephyr_z9 · 2026-10-26
- CoreWeave 5-year CDS spikes to ~1,100bps as market fears AI bubble starts as credit event — kimmonismus · 2026-10-26
- AI demand reshapes cloud computing: scarce capacity and long-term deals replace on-demand — DavidLinthicum · 2026-10-26