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-Instruct

All quants made using imatrix option with dataset from here

You can use them with a recent version of llama.cpp, or any project based on it.

Downloads last month
440
GGUF
Hardware compatibility
Log In to view the estimation

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for essigpeng/Qwen3-Next-80B-A3B-Instruct-GGUF

Quantized
(65)
this model