Kimi K2.5

Overview

Moonshot AI's 1-trillion-parameter MoE with 32B active parameters and a multimodal agent-swarm mode. Around 595GB on disk, aimed at serious home labs and small clusters.

When to pick this model

• Multi-agent orchestration with swarm-mode coordination
• Frontier-scale local inference on a home lab cluster
• Long-context multimodal workflows up to 256K tokens
• Research into trillion-parameter models
• Replacing closed APIs at the high end

VRAM requirements by quantization

Quantization	VRAM required
Q4_K_M (recommended)	600 GB
Q5_K_M	720 GB
Q8_0	1080 GB
FP16 (no quantization)	2000 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

• Genuine 1-trillion-parameter open-weight model
• Built-in agent swarm coordination mode
• 256K context with multimodal input
• Only 32B active parameters per token

Limitations

• ~600GB in Q4 demands a small cluster
• Modified MIT license needs legal review for commercial use
• Operational complexity is extreme
• Power and cooling budget rules out most home setups

Architecture & training

Architecture: MoE 1T/32B active · multimodal · 'agent swarm' mode · 256k ctx

Training: The largest practical open-weight model.

Quick start

# HuggingFace : moonshotai/Kimi-K2.5

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.