Powers Cursor Composer 2 — the industry benchmark for agentic coding. #2 on the Artificial Analysis Intelligence Index. 1T total parameters with 32B active, delivering near-frontier reasoning at extreme scale.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 302GB VRAM Recommended
The Kimi-K2.5 model by Moonshot AI is a 1T (MoE) parameter architecture optimized for reasoning tasks. It requires approximately 300GB of VRAM to comfortably run locally using a Q4_K_M quantization. Extending the context window up to 262,144 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running Kimi-K2.5 at maximum tokens-per-second, we recommend using LM Studio or Ollama with a GGUF quantization (Q4_K_M or Q6_K). If you are multi-GPU, use vLLM to distribute the layers across your VRAM pool for optimal throughput.
You will need a GPU with at least 302GB of VRAM to run the Q4_K_M quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run kimi-k2.5' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.