How to Run Kimi K2.7 Code Locally: Setup Guide for Moonshot AI's Agentic Coding Model
Summary
A step-by-step guide to running Kimi K2.7 Code locally. Kimi K2.7 Code is Moonshot AI's agentic coding model built on K2.6, featuring improved task completion with ~30% fewer thinking tokens. It's a 1T-parameter (32B active) MoE model supporting thinking, vision, and 256K context, with SOTA performance across vision, coding, agentic, long-context, and chat tasks. Full precision requires 605GB disk space; Unsloth Dynamic 2-bit reduces this to 325GB (-48%). The guide covers running via Unsloth Studio or llama.cpp using GGUF format.
Source
unsloth.aiHow to Run Kimi K2.7 Code Locally: Setup Guide for Moonshot AI's Agentic Coding Modelunsloth.aiKey quotes
· 4 pulledKimi K2.7 Code is Moonshot AI's agentic coding model, building on K2.6 to improve task completion while using ~30% fewer thinking tokens.
The 1T-parameter (32B active) MoE model supports thinking only, vision and 256K context.
It delivers SOTA open performance across vision, coding, agentic, long-context, and chat tasks.
Full precision requires 605GB of disk space; Unsloth Dynamic 2-bit requires 325GB (-48%).
You might also wanna read
Moonshot AI Develops Kimi K2: A Cutting-Edge Language Model with 32 Billion Parameters
Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters d
github.com·11mo ago
AWS Marketplace: Kimi API Platform
aws.amazon.com·8d ago
Kimi K2.6 Open-Source Coding Model Released with Advanced Capabilities
Kimi K2.6 is an open-source coding model featuring state-of-the-art capabilities including long-horizon execution, agent swarm functionality
Moonshot Kimi-K2.5 Technical Documentation and GitHub AI Development Tools Overview
The article appears to be a technical report or documentation for Moonshot's Kimi-K2.5 AI model, hosted on GitHub. It includes information a
github.com·5mo ago
NVIDIA Releases Kimi-K2.6 DFlash Language Model with Speculative Decoding on Hugging Face
NVIDIA has released the Kimi-K2.6 DFlash model on Hugging Face, a draft head for Moonshot AI's Kimi-K2.6 auto-regressive language model. It
Moonshot's Kimi K2 Thinking: An Open-Source Thinking Model
The article discusses Kimi K2 Thinking, an open-source thinking model developed by Moonshot. It appears to be a technology-focused piece abo
moonshotai.github.io·7mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.