[Megathread] Qwen 3.8 27B Release Day
热度趋势
趋势数据积累中
百分比基于当前可用热度信号，而非评论数或独立用户人数。
Qwen 相关模型动态已经出现，适合跟踪能力变化、生态影响和后续可用性。
为了整合关于 Qwen 3.8 27B 发布的讨论，社区创建了一个大型主题帖。该主题帖涵盖了量化、微调与消融、聊天模板以及推理服务器支持与配置等多个方面。此外，它还提供了 Qwen3.8-27B 和 Qwen3.8-27B-FP8 的官方 Hugging Face 链接，以及 Qwen3.8-27B-GGUF 和 MLX 社区的 bf16、8bit、4bit…
Megathread to help with the influx of duplicate / similar posts around the release of the Qwen 3.8 27B release.
- Quants
- Fine-Tunes & Abliterations
- Chat Templates
- Inference Server Support & Configuration
- Experiences, Benchmarks & Model Comparisons
Official:
- https://huggingface.co/Qwen/Qwen3.8-27B
- https://huggingface.co/Qwen/Qwen3.8-27B-FP8
Popular:
- https://huggingface.co/unsloth/Qwen3.8-27B-GGUF
- https://huggingface.co/bartowski/Qwen3.8-27B-GGUF
- https://huggingface.co/mlx-community/Qwen3.8-27B-MTP-bf16
- https://huggingface.co/mlx-community/Qwen3.8-27B-MTP-8bit
- https://huggingface.co/mlx-community/Qwen3.8-27B-MTP-4bit
We'll try to clean up future duplicates around the release and point them here.