mradermacher/Qwen3.8-27B-Uncensored-Cyber-i1-GGUF

🤗 Hugging Face 来源image-text-to-textapache-2.0激活 27B219 GBGGUF✓ 15 个校验和今天更新
已有模型文件?提交模型种子

如果你有完整的模型文件并有权分享,请把示例文件夹路径替换为你的文件路径,再运行这条命令。它会校验文件、制作种子,并将磁力链接和校验和提交给 Pirate Face。请让种子客户端持续做种,方便其他人从节点下载。Pirate Face 不接收模型文件。你可以从账户页面获取社区密钥。也可以先阅读脚本。

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo mradermacher/Qwen3.8-27B-Uncensored-Cyber-i1-GGUF ./model-folder
需要做种者 →

About

weighted/imatrix quants of https://huggingface.co/HFCK99/Qwen3.8-27B-Uncensored-Cyber

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/Qwen3.8-27B-Uncensored-Cyber-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF imatrix 0.1 imatrix file (for creating your own quants)
GGUF i1-Q2_K 11.0 IQ3_XXS probably better
GGUF i1-Q3_K_S 12.4 IQ3_XS probably better
GGUF i1-IQ3_S 12.7 beats Q3_K*
GGUF i1-IQ3_M 12.9
GGUF i1-Q3_K_M 13.6 IQ3_S probably better
GGUF i1-Q3_K_L 14.7 IQ3_M probably better
GGUF i1-IQ4_XS 15.4
GGUF i1-Q4_0 15.9 fast, low quality
GGUF i1-Q4_K_S 15.9 optimal size/speed/quality
GGUF i1-Q4_K_M 16.9 fast, recommended
GGUF i1-Q4_1 17.4
GGUF i1-Q5_K_S 19.1
GGUF i1-Q5_K_M 19.6
GGUF i1-Q6_K 22.5 practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.