Kimi K2 models

5 Kimi K2 models from Moonshot AI on Hugging Face, from 3.0B to 1026.9B parameters, published by Moonshot AI in F8_E4M3 and Native INT4, with contexts from 128K to 256K tokens. The smallest official model, Kimi-K2.5, needs about 1128 GB of VRAM at its published precision; the cheapest live fit is AMD MI300X at $15.77/hr.

Part of the Kimi series · Next generation: Kimi K3

Pick a size

One row per official Kimi K2 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
Kimi-K2-Instruct1026.4B1147 GB–574 GBAMD MI300X × 6$15.77/hr2.1 GB
Kimi-K2-Instruct-09051026.5B1147 GB–574 GBAMD MI300X × 6$15.77/hr2.1 GB
Kimi-K2.51026.9B1128 GB––AMD MI300X × 6$15.77/hr2.1 GB

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Kimi-K2-Instruct1026.4BF8_E4M31147 GBAMD MI300X × 6$15.77/hr
Kimi-K2-Base1026.5BF8_E4M31147 GBAMD MI300X × 6$15.77/hr
Kimi-K2-Instruct-09051026.5BF8_E4M31147 GBAMD MI300X × 6$15.77/hr
Kimi-K2.51026.9BNative INT41128 GBAMD MI300X × 6$15.77/hr

Fine-tunes and community models (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
kimi-k2.6-eagle3-mla3.0BBF166.7 GBRTX 3070$0.088/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

More from Moonshot AI

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.