Kimi K2 models
5 Kimi K2 models on Hugging Face, from 3.0B to 1026.9B parameters. At the precision each one is published in, the smallest needs about 6.7 GB of VRAM (kimi-k2.6-eagle3-mla, cheapest live fit: RTX 5060 Ti) and the largest about 1147 GB (Kimi-K2-Instruct-0905). The cheapest way to run kimi-k2.6-eagle3-mla is $0.110/hr.
Kimi K2 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| kimi-k2.6-eagle3-mla | 3.0B | BF16 | 6.7 GB | RTX 5060 Ti | $0.110/hr |
| Kimi-K2-Instruct | 1026.4B | F8_E4M3 | 1147 GB | No live fit | – |
| Kimi-K2-Base | 1026.5B | F8_E4M3 | 1147 GB | No live fit | – |
| Kimi-K2-Instruct-0905 | 1026.5B | F8_E4M3 | 1147 GB | No live fit | – |
| Kimi-K2.5 | 1026.9B | Native INT4 | 1128 GB | No live fit | – |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; 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
- Kimi K3 (3 models)
