Store › model › LLM

Kwaipilot_KAT-Coder-V2.5-Dev-GGUF

by bartowski · source Hugging Face · updated 2026-07-24

apache-2.020 GB~24 GB RAMsource aliveunlabeled

Llamacpp imatrix Quantizations of KAT-Coder-V2.5-Dev by Kwaipilot

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF and its progress lives in the Resource Center.

Source and license

• Source: https://huggingface.co/bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF
• License: apache-2.0
• Requirements: about 24 GB of RAM, 20 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
• Tags: gguf code agent agentic-coding moe coding text-generation en zh endpoints_compatible imatrix conversational

Numbers

• 313,246 downloads on Hugging Face
• 138 likes
• license apache-2.0
• 20 GB for Kwaipilot_KAT-Coder-V2.5-Dev-Q4_K_M.gguf
• 327,838 npm downloads a week for node-llama-cpp
• latest node-llama-cpp@3.22.1

Numbers as of 2026-10-02 21:01 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

From the source README

system
{system_prompt}
user
{prompt}
assistant

Card id model:hf:bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF · collected 2026-10-02 21:01 UTC · JSON