Vision
How to deploy Kimi K2.5 on a GPU cloud
A 1T-parameter (32B active) native multimodal agentic model. Full specs, license and use cases.
Kimi K2.5 size and hardware requirements
1026.9B
Total parameters
Mixture-of-experts: 32B active parameters (stated on the model card)
Active parameters
Native INT4
Published precision
1128.0 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| Native INT4 (native) | 554.3 GB | 1128.0 GB | AMD MI300X | 6 | $15.77/hr |
How to run Kimi K2.5
Run Kimi K2.5 with vLLM
From moonshotai/Kimi-K2.5's own deployment guide: an example serving it on a single H200 node at tensor-parallel-8.
vllm serve $MODEL_PATH -tp 8 --mm-encoder-tp-mode data --trust-remote-code --tool-call-parser kimi_k2 --reasoning-parser kimi_k2Source: https://huggingface.co/moonshotai/Kimi-K2.5/raw/main/docs/deploy_guidance.md
Run Kimi K2.5 with SGLang
From moonshotai/Kimi-K2.5's own deployment guide, same single H200 node at tensor-parallel-8.
sglang serve --model-path $MODEL_PATH --tp 8 --trust-remote-code --tool-call-parser kimi_k2 --reasoning-parser kimi_k2Source: https://huggingface.co/moonshotai/Kimi-K2.5/raw/main/docs/deploy_guidance.md
Deploy Kimi K2.5 on Aquanode
Aquanode has no one-click deploy template for Kimi K2.5; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (6× AMD MI300X or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod