Kimi-K2.6 — which GPUs fit

Moonshot · 1030.0B (active 32.0B) · MoE · ctx 256K · Modified MIT · HuggingFace

Kimi-K2.6 (Moonshot) is a 1030.0B parameters MoE (32.0B active per token) open-weight model tracked on AI Hashrate. At 8K context we estimate roughly 573.9 GB VRAM for Q4 (weights 566.5 GB + KV 6.4 GB + 1 GB overhead) and 2067.4 GB for FP16. About 0 GPUs/accelerators in our catalog fully fit this model at Q4 under that context assumption. Fastest Q4 configs: B200 192GB SXM ≈ 50.9 tok/s (estimated); MI300X 192GB ≈ 33.7 tok/s (estimated); Mac Studio M2 Ultra 192GB ≈ 5.1 tok/s (estimated). Use the table below for VRAM fit and tok/s per dollar (list MSRP). Estimates follow memory-bandwidth math; measured rows override when present. See methodology for details. Methodology.

3 hardware configs — sorted by tok/s. Default fit context 8K.

Hardware	VRAM	Quant	tok/s	Fits?	tok/s/$
B200 192GB SXM	192	Q4	50.9 est.	No	0.001
MI300X 192GB	192	Q4	33.7 est.	No	0.002
Mac Studio M2 Ultra 192GB	192	Q4	5.1 est.	No	0.001

Fit checks

Mac Studio M2 Ultra 192GB — does not fit · ≈5.1 tok/s Q4 est.

12 popular retail GPUs; every row in the table above also links its Fits? verdict to the full fit check.