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.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Kimi-K2-Instruct | 1026.4B | 1147 GB | – | 574 GB | AMD MI300X × 6 | $15.77/hr | 2.1 GB |
| Kimi-K2-Instruct-0905 | 1026.5B | 1147 GB | – | 574 GB | AMD MI300X × 6 | $15.77/hr | 2.1 GB |
| Kimi-K2.5 | 1026.9B | 1128 GB | – | – | AMD MI300X × 6 | $15.77/hr | 2.1 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)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Kimi-K2-Instruct | 1026.4B | F8_E4M3 | 1147 GB | AMD MI300X × 6 | $15.77/hr |
| Kimi-K2-Base | 1026.5B | F8_E4M3 | 1147 GB | AMD MI300X × 6 | $15.77/hr |
| Kimi-K2-Instruct-0905 | 1026.5B | F8_E4M3 | 1147 GB | AMD MI300X × 6 | $15.77/hr |
| Kimi-K2.5 | 1026.9B | Native INT4 | 1128 GB | AMD MI300X × 6 | $15.77/hr |
Fine-tunes and community models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| kimi-k2.6-eagle3-mla | 3.0B | BF16 | 6.7 GB | RTX 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
- Kimi K3 (3 models)
- Kimi VL (1 models)
- moonshotai (1 models)
- Moonlight (2 models)