Llama.cpp imatrix Quantizations of Qwen3-Next-80B-A3B-Thinking by Qwen
Using llama.cpp release b7206 for quantization.
Original model: https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking
All quants made using imatrix option with dataset from here
You can run them with recent versions of llama.cpp, or any project based on it.
- Downloads last month
- 171
Hardware compatibility
Log In
to view the estimation
4-bit
Model tree for essigpeng/Qwen3-Next-80B-A3B-Thinking-GGUF
Base model
Qwen/Qwen3-Next-80B-A3B-Thinking