Kimi K3 models
3 Kimi K3 models on Hugging Face, from 2.2B to 3.6B parameters. At the precision each one is published in, the smallest needs about 5.0 GB of VRAM (Kimi-K3-DSpark, cheapest live fit: RTX 5060 Ti) and the largest about 8.0 GB (Kimi-K3-DSpark, cheapest live fit: RTX 5060 Ti). The cheapest way to run Kimi-K3-DSpark is $0.110/hr.
Kimi K3 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Kimi-K3-DSpark | 2.2B | BF16 | 5.0 GB | RTX 5060 Ti | $0.110/hr |
| Kimi-K3-DFlash | 2.6B | BF16 | 5.8 GB | RTX 5060 Ti | $0.110/hr |
| Kimi-K3-DSpark | 3.6B | BF16 | 8.0 GB | RTX 5060 Ti | $0.110/hr |
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 K2 (5 models)
