shiiiiiiiiiiiiiiiiiiiiiiiiiiiii/DeepSeek-V4-Flash-0731-K160-REAP-GGUF overview
Repository moved This repository has moved to a new location. 👉 DeepSeek V4 Flash 0731 K160 REAP GGUF https://huggingface.co/shi0203/DeepSeek V4 Flash 0731 K1…
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Browse files on Hugging Face | ||||
Model Details
| Model ID | shiiiiiiiiiiiiiiiiiiiiiiiiiiiii/DeepSeek-V4-Flash-0731-K160-REAP-GGUF |
|---|---|
| Author | shiiiiiiiiiiiiiiiiiiiiiiiiiiiii |
| Pipeline | — |
| License | mit |
| Base model | — |
| Last modified | 2026-08-19T07:37:55.000Z |
Model README
---
license: mit
---
Repository moved
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.
About the model
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.
Run shiiiiiiiiiiiiiiiiiiiiiiiiiiiii/DeepSeek-V4-Flash-0731-K160-REAP-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models