neopolita / Niwaki-Qwen3.8-Flash-Next-141B-A6B-v4.0-gguf
Text Generation7301Updated Oct 14, 2026
Downloads
730
Likes
1
Last updated
Oct 14, 2026
License
other
GGUF build of Niwaki-Qwen3.8-Flash-Next-141B-A6B-v4.0-mlx — Qwen3.8-Flash-Next at 141B total / ~5.9B active parameters, with the program-state behaviours we test at the unpruned model's level — for llama.cpp on CUDA, Vulkan, Metal and CPU. One 61.7 GB file: 18% lower perplexit…
Tasks & library
- text generation
- gguf
Tags
- gguf
- llama.cpp
- moe
- pruning
- quantization
- mixture-of-experts
Technical specifications
ParametersNot available
Librarygguf
LanguagesNot available
Licenseother