从语言到影像，从开源到 API。读懂模型能力、比较真实成本，
为你的下一个想法，找到合适的智能引擎。
This is an uncensored version of unsloth/gpt-oss-20b-BF16 created with abliteration (see remove-refusals-with-transformers to know more about it). You can use this model in your applications by loading it with Hugging Face's `transformers` library:
译文排队中 · 当前显示来源原文
This model is a fine-tuned version of huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated. It has been trained using TRL. Please refer to Quantization-Aware Training (QAT) for fine-tuning and quantization(huihui-ai/Huihui-gpt-oss-20b-mxfp4-abliterated-v2). **Advantages**: All core metrics (Loss/Acc/Entropy) improve synchronously, with a small gap between Eval and Train (<0.01), indicating strong generalization ability. Fine-tuning shows effect in just 400 steps, with high efficiency.
译文排队中 · 当前显示来源原文
This is a mxfp4 version of huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated-v2 Reference OpenAI GPT-OSS Quantization Aware Training (QAT) & Quantized Deployment Ollama requires the latest version: v0.11.8
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
We re-quantized the models using llama.cpp and have uploaded the Q2, Q3, Q4, Q5, Q6, Q8, and BF16 quantized models. Stock llama.cpp does not support the `kolibri1` architecture yet. Apply `kolibri1-llama.cpp.patch` (included in this repo) to llama.cpp at upstream commit `836d571`, then build:
译文排队中 · 当前显示来源原文
This is an uncensored version of poolside/Laguna-S-2.1 created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. **Note** This is an English language model, and support for other languages is not very good. - **Risk of Sensitive or Controversial Outputs**: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
This is an uncensored version of mistralai/Mistral-Small-3.2-24B-Instruct-2506 created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. If you like it, please click 'like' and follow us for more updates. You can follow x.com/support_huihui to get the latest model information from huihui.ai.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
This is an uncensored version of TokenRhythm/NeoHorse-1-4B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. The MTP and Visual components were extracted from the original Qwen/Qwen3.5-4B and can provide excellent support.
译文排队中 · 当前显示来源原文
This is an uncensored version of deepreinforce-ai/Ornith-1.0-9B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. **Note** We will directly perform ablation on the GGUF files from protoLabsAI/Ornith-1.0-9B-MTP-GGUF. Some weights quantized in Q3_K, Q4_K, Q5_K and Q6_K will be converted to Q8_0. This time, the weights of the first 5 layers, so the final weights will increase, but the change will not be significant. We performed a simple quantization comparison between Q8_0 and MXFP4 on the Q3 version of protoLabsAI/Ornith-1.0-9B-MTP-GGUF.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
This is an uncensored version of Mia-AiLab/Qwable-3.6-27b created with abliteration. This ablation was performed entirely using llama.cpp's GGUF model, without relying on Transformers, For the specific ablation method, please refer to cvector-generator.
译文排队中 · 当前显示来源原文
This is an uncensored version of Mia-AiLab/Qwable-3.6-27b created with abliteration. This ablation was performed entirely using llama.cpp's GGUF model, without relying on Transformers, For the specific ablation method, please refer to cvector-generator.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
This is an uncensored version of Qwen/Qwen3-30B-A3B-Instruct-2507 created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. Ablation was performed using a new and faster method, which yields better results. You can use huihui_ai/qwen3-abliterated:30b-a3b-instruct-2507-q4_K_M directly,
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
可以调整厂商、分类或输入输出条件；新模型正持续收录。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。
