NOTICE
| 1 | Qwen3.8-27B iMatrix NVFP4 MTP GGUF |
| 2 | Copyright 2026 Michał Piszczek |
| 3 | |
| 4 | This package is a quantized derivative of Qwen/Qwen3.8-27B. The base model is |
| 5 | licensed under the Apache License 2.0. The F16 multimodal projector is an |
| 6 | unchanged copy from the Unsloth GGUF conversion and retains that provenance. |
| 7 | |
| 8 | Base model: https://huggingface.co/Qwen/Qwen3.8-27B |
| 9 | Conversion source: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF |
| 10 | Benchmark notes: https://piszczek.pl/blog/qwen38-27b-256k-50-tps-24gb-gpu |
| 11 | |