Modelpublic

zaydiscold/Qwopus3.6-27B-v2-IQ4_XS-GGUF

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

1likes15downloads

Model Card

Qwopus3.6-27B-v2 IQ4_XS GGUF

IQ4_XS quantization of `Jackrong/Qwopus3.6-27B-v2` via stock llama.cpp (ggml-org/llama.cpp), built on Apple Silicon with Metal support. Preserves MTP draft heads.

Use

bash

llama-cli -m Qwopus3.6-27B-v2-IQ4_XS.gguf -p "Hi"

Author's temperature recommendation: 0.75–1.0.

Credits

—Source: `Jackrong/Qwopus3.6-27B-v2` by Jackrong
—GGUF conversion by zaydiscold

Mix brought by the NOTORIOUS MLX.