LocalClaw/LLM/Kimi K2.5 (1T MoE)
Open-weight MoE

Kimi K2.5 (1T MoE)

Catalogue summary: Moonshot AI open-weight multimodal agentic MoE with 1T total parameters and 32B active per token. The verified Q4_K_M GGUF is roughly 621.2 GB, making this a server-grade local target. The legacy route ID keeps its active-parameter shorthand for URL stability. Modified MIT licence.

Repository editorial metadata; verify comparative claims in the linked upstream material.

1024 GB catalogue minimum1024 GB RAMQ4_K_MCoding assistant
Choose an app

Only verified options can be opened. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
Open in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
1T (32B active, MoE)
Minimum RAM
1024 GB
Model size
621.2 GB
Quantization
Q4_K_M

Can Kimi K2.5 (1T MoE) run locally?

Kimi K2.5 (1T MoE) has a catalogue minimum of 1024 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Treat kimi-k2.5 as a server-grade catalogue target. Use the verified artefact with a compatible multi-GPU or distributed runtime and follow its upstream instructions; this is not a one-click desktop LM Studio recommendation.

Model sourcePublic GGUF repository (verified 2026-09-07): unsloth/Kimi-K2.5-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningserver-gradequalitymoemultimodal

Deployment path

01
Check RAM fitServer-grade target. Plan for 1024 GB class multi-GPU memory.
02
Load the modelUse kimi-k2.5 only with a compatible server-grade or distributed runtime; confirm the exact artefact and upstream instructions first.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: kimi
  • Parameters: 1T (32B active, MoE)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 1024 GB
  • Catalogue model size: 621.2 GB
  • Tags: chat, code, reasoning, server-grade, quality, moe, multimodal

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • server-grade
  • quality
  • moe

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
4
quality
10
coding
10
reasoning
10

Technical notes

Developer
Moonshot AI
License
Modified MIT
Context window
262,144 tokens
Architecture
Mixture of Experts — 1T total, 32B active

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Very large memoryMac Studio Ultra classCheck model size firstNVIDIA GB10 / server optionsMore practical alternativesCompare smaller models

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Kimi K2 Instruct (1T MoE) 1T (32B active, 384 experts)Kimi K2.7 Code (1T MoE) 1T (32B active)Kimi K2 Thinking (1T MoE) 1T (32B active, 384 experts)DeepSeek V4 Pro (1.6T MoE) 1.6T (49B active)Ling 1T (1T MoE) 1T (50B active)MiMo-V2.5-Pro (1.02T MoE) 1.02T (42B active)

Where to go next