Qwen3.8-27B UD-IQ4_XS GGUF

This repository publishes the local file Qwen3.8-27B-UD-IQ4_XS.gguf (14,252,845,984 bytes). groxaxo did not quantize it.

The GGUF header records:

• general.architecture: qwen35
• general.name: Qwen3.8-27B
• general.license: apache-2.0
• general.quantized_by: Unsloth
• general.file_type: 30
• general.base_model.0.repo_url: https://huggingface.co/Qwen/Qwen3.8-27B
• quantize.imatrix.file: Qwen3.8-27B-GGUF/imatrix_unsloth.gguf
• quantize.imatrix.entries_count: 496
• quantize.imatrix.chunks_count: 1251

The same filename is already published at unsloth/Qwen3.8-27B-GGUF. SHA256SUMS is the SHA-256 of the file uploaded from this Mac.

Use

Load the GGUF with llama.cpp or another GGUF runner. This is not an MLX checkpoint. No new quality measurement was made for this upload.