Downloads · 30 days
12
6% of all-time downloads
shiiiiiiiiiiiiiiiiiiiiiiiiiiiii
shiiiiiiiiiiiiiiiiiiiiiiiiiiiii/DeepSeek-V4-Flash-0731-K160-REAP-GGUF
DeepSeek-V4-Flash-0731-K160-REAP-GGUF is a machine learning model from shiiiiiiiiiiiiiiiiiiiiiiiiiiiii. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository has moved to a new location.
Downloads · 30 days
12
6% of all-time downloads
All-time downloads
204
Public
Repo size
58.8 GB
Likes
0
Public
Click a slice to open those files.
.md893 B · 100%
From the Hugging Face model README
This repository has moved to a new location.
👉 DeepSeek-V4-Flash-0731-K160-REAP-GGUF
All model files, documentation, updates, and future quantization variants are now maintained in the new repository.
The model files have been removed from this repository to avoid maintaining duplicate copies.
Please use the new repository for downloads and future updates.
This is an experimental REAP K160 compact GGUF variant of DeepSeek V4 Flash 0731.
The current Q2 version is built from the working asymmetric/mixed Q2 GGUF by removing the routed experts excluded by the 0xSero K160 REAP expert selection, rather than quantizing the already-pruned K160 checkpoint again.
Future variants and evaluation results will be published in the new repository.