サイト内検索
AI モデル 84760
- siglip2-so400m-patch16-512-jax↗
Google
- t5-efficient-large-nh12↗
Google
- t5gemma-xl-xl-ul2-it↗
Google
- smollm-135M-instruct-add-basics-q0f16-MLC↗
HuggingFaceTB
- Hy-SimulMT-30B-A3B-GGUF↗
腾讯
- CoRM-469M-top1↗
ilsp
- Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF↗
IsValorum
If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies. Official **VAL-APEX-I NanoPlus V3** quantization of **ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-MTP**. This edition quantizes the uncensored foundation model built on UkisAI's Swift-1.5 reasoning fine-tune of Qwen3.8-27B with the V3 NanoPlus allocation (`IQ3_XXS` in the core MLP blocks, `IQ4_XS` on the outer layers 0-7 and 56-63, attention and recurrent matrices protected). VAL-APEX-I stands for: **Vector-calibrated Asymmetric Layer-wise Outlier-preserving Recurrent-aware Unified Matrix-quantization**
- quantization-gptq↗
kernels-community
- rotary↗
kernels-community
> [!CAUTION] > Starting from September 13, 2026, we will be removing the "model" type repositories of kernels (e.g., kernels-community/flash-attn3). Make sure you're using a latest version of kernels. If you face any disruption, please report them here: https://github.com/huggingface/kernels/issues/new. This is the repository card of kernels-community/rotary that has been pushed on the Hub. It was built to be used with the `kernels` library. This card was automatically generated. Benchmarking script is available for this kernel. Run `kernels benchmark kernels-community/rotary --version `.
- Gemmasutra-Mini-2B-v1-gguf↗
l3utterfly