Qwen3.8-27B-Uncensored-NVFP4
FP4-quantized build of orcarouter/Qwen3.8-27B-Uncensored (BF16), preserving the abliteration edits byte-for-byte — this is a quantization of the uncensored...
FP4-quantized build of orcarouter/Qwen3.8-27B-Uncensored (BF16), preserving the abliteration edits byte-for-byte — this is a quantization of the uncensored...
> Bugfix release on top of Nova-1-0.8B: pair-tuned to stop hallucinating tool calls on prompts that need a...
weighted/imatrix quants of https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash For a convenient overview and download list, visit our model page for this model....
static quants of https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash For a convenient overview and download list, visit our model page for this model....
A full-weight checkpoint that adapts Qwen3.8-27B for Korean conversation along two axes. 1. Style alignment — trained on...
The original BF16 release had extra wrapper prefixes in its Safetensors headers and index. Stock loaders could therefore...
> Versioning notice: This card describes the current OTel 2.0 QLoRA checkpoint. The model weights may be updated...
— Model Architecture: GLM-5.3-Flash — Input: Text, Image — Output: Text — Model Optimizations: — Weight quantization: INT4...
👋 Присоединяйтесь к сообществу WeChat или Discord. 📖 Ознакомьтесь с блогом GLM-5.3-Flash и техническим отчетом GLM-5. 📍 Используйте...
Квантование сообщества EXL3 ornith-ai/Ornith-1.5-35B-A3B. Не официальный релиз Орнит. Большинство квантов EXL3 в моделях MoE используют переключатель -hq, который...