tensorblock/KwaiCoder-23B-A4B-v1-GGUF

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

Kwaipilot/KwaiCoder-23B-A4B-v1 - GGUF

This repo contains GGUF format model files for Kwaipilot/KwaiCoder-23B-A4B-v1.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

Our projects

Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.

Model file specification

Filename	Quant type	File Size	Description
KwaiCoder-23B-A4B-v1-Q2_K.gguf	Q2_K	9.475 GB	smallest, significant quality loss - not recommended for most purposes
KwaiCoder-23B-A4B-v1-Q3_K_S.gguf	Q3_K_S	11.022 GB	very small, high quality loss
KwaiCoder-23B-A4B-v1-Q3_K_M.gguf	Q3_K_M	12.039 GB	very small, high quality loss
KwaiCoder-23B-A4B-v1-Q3_K_L.gguf	Q3_K_L	12.547 GB	small, substantial quality loss
KwaiCoder-23B-A4B-v1-Q4_0.gguf	Q4_0	13.134 GB	legacy; small, very high quality loss - prefer using Q3_K_M
KwaiCoder-23B-A4B-v1-Q4_K_S.gguf	Q4_K_S	14.089 GB	small, greater quality loss
KwaiCoder-23B-A4B-v1-Q4_K_M.gguf	Q4_K_M	15.431 GB	medium, balanced quality - recommended
KwaiCoder-23B-A4B-v1-Q5_0.gguf	Q5_0	16.023 GB	legacy; medium, balanced quality - prefer using Q4_K_M
KwaiCoder-23B-A4B-v1-Q5_K_S.gguf	Q5_K_S	16.474 GB	large, low quality loss - recommended
KwaiCoder-23B-A4B-v1-Q5_K_M.gguf	Q5_K_M	17.624 GB	large, very low quality loss - recommended
KwaiCoder-23B-A4B-v1-Q6_K.gguf	Q6_K	20.841 GB	very large, extremely low quality loss
KwaiCoder-23B-A4B-v1-Q8_0.gguf	Q8_0	24.724 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/KwaiCoder-23B-A4B-v1-GGUF --include "KwaiCoder-23B-A4B-v1-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/KwaiCoder-23B-A4B-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'