 | I just used the new Apex Quantization on QWEN Coder 80B Created an Important Matrix using Code examples This should be the fastest best at coding 80B Next Coder around It's what I'm using for STACKS! so I thought I would share with the community It's insanely fast and the size has been shrunk down to 54.1GB https://huggingface.co/stacksnathan/Qwen3-Coder-Next-80B-APEX-I-Quality-GGUF [link] [comments] |
