Model ID
moonshotai/Kimi-K3
Capabilities
Kimi K3
Kimi K3 is a frontier-scale native multimodal Mixture-of-Experts model designed for long-horizon reasoning, agentic coding, and large-scale knowledge workflows. It is the world's first open 3T-class model, featuring 2.8T total parameters with 104B activated, built on a 93-layer architecture with Kimi Delta Attention (KDA), Gated MLA, and Stable LatentMoE. The model uses a 7,168 hidden size, 96 attention heads, and 896 routed experts, activating 16 experts per token alongside 2 shared experts. Powered by MoonViT-V2 for native vision understanding and supporting a 1M-token context window, Kimi K3 is optimized for multimodal reasoning, long-context coding, advanced agentic workflows, and frontier-scale research applications
About this model
Kimi K3 is a frontier-scale native multimodal Mixture-of-Experts model designed for long-horizon reasoning, agentic coding, and large-scale knowledge workflows. It is the world's first open 3T-class model, featuring 2.8T total parameters with 104B activated, built on a 93-layer architecture with Kimi Delta Attention (KDA), Gated MLA, and Stable LatentMoE. The model uses a 7,168 hidden size, 96 attention heads, and 896 routed experts, activating 16 experts per token alongside 2 shared experts. Powered by MoonViT-V2 for native vision understanding and supporting a 1M-token context window, Kimi K3 is optimized for multimodal reasoning, long-context coding, advanced agentic workflows, and frontier-scale research applications
Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (moonshotai/Kimi-K3). Released under Kimi-K3. Further reading: Paper · Blog
Deploy Private Inference Endpoint
Choose your hardware and inference engine to get deployment commands and performance benchmarks tailored to your infrastructure
Hardware
MI355X
2,304 GB
Engine
vLLM
SGLang
Deployment code
Access Restricted
Enter your email to get access to this content
Requires the vllm/vllm-openai-rocm:kimi-k3 Docker image or a standard vLLM image version greater than v0.26.0.
Performance under load
Tokens/s (total)
Benchmarks measured by Vultr on MI355X · vLLM. Throughput and latency vary with concurrency, input length and engine configuration, so treat these as a comparison baseline, not a service guarantee.
AMD Instinct MI355X
Unlock Next-Generation AI Power on Vultr Cloud GPU