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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 84838
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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗This repository contains a full spectrum of GGUF quantizations for lukey03's Qwen3.5-9B-abliterated. These files are optimized for local inference using llama.cpp, LM Studio, Jan, Ollama, and other compatible software. The base model is a fully uncensored version of Qwen3.5-9B. It achieved a **0% refusal rate** (answering 100% of controversial/restricted prompts) through a two-stage process: 1. **Orthogonal Projection (Abliteration):** Surgically removing the "refusal direction" from the residual stream across all 32 layers. 2. **LoRA Fine-tuning:** Targeted training to eliminate the remaining stubborn refusal categories.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗This repository contains GGUF quantizations of the heavily fine-tuned and uncensored AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored model. Unlike standard quantization, these models were generated using a high-precision pipeline: * **Output Tensor Preservation:** We utilized `--leave-output-tensor` during quantization. This ensures the model's final projection head remains in `FP16` precision, preventing the "numerical noise" that typically degrades the reasoning capabilities of smaller quantizations. * **SSM Weight Fidelity:** The 1D SSM routing weights (alpha/beta) were preserved to maintain the model's complex long-range memory and selective state dynamics. * **Native Reasoning:** The model is equipped with a native reasoning trigger. By utilizing the built-in ` ` block, the model can perform multi-step logical planning before providing a final response. These files are prefixed with `Qwen3.6-27B...`. They are generated using `--leave-output-tensor`, ensuring the final projection head and 1D SSM routing weights are preserved at higher precision. **These provide superior reasoning, logic retention, and intelligence.**
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗These files were quantized by Abiray using `llama.cpp` to make the model accessible for consumer hardware and CPU-heavy environments. I have processed this model into several different quantization formats. You can find them in my other repositories: * Abiray/Qwen3.6-35B-A3B-Q8_0-GGUF (High quality, largest file) * Abiray/Qwen3.6-35B-A3B-Q6_K-GGUF (Very high quality) * Abiray/Qwen3.6-35B-A3B-Q5_K_M-GGUF (Great balance of quality and size) * Abiray/Qwen3.6-35B-A3B-Q4_K_M-GGUF (Good quality, recommended for most users) * Abiray/Qwen3.6-35B-A3B-Q3_K_M-GGUF (Low quality, smallest file)
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Qwen3.8-27B-Q4_K_M-GGUF
AbirayThis repository contains the GGUF format quantization of the Qwen3.8-27B model, a native vision-language model. Qwen3.8-27B is the most capable generation in the Qwen open-model family, built on the architectural foundation of Qwen3.5. It is a native vision-language model that understands images and videos, delivering substantial gains across coding, professional work, research, and long-horizon agentic tasks. This GGUF file is compatible with popular local LLM inference tools. When configuring the model in your preferred client, ensure you attach the mmproj-F16.gguf file in the "Vision Adapter" or "Multimedia Projection" setting to enable image processing. The original model was developed and released by the Qwen Team.
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗A standalone, **weight-baked uncensored & abliterated GGUF** of **`ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF`.** This build is created by precisely transplanting 144 orthogonalized residual-writing tensors from **`orcarouter/Qwen3.8-Flash-Next-Uncensored`** (via `SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF`) directly into the optimized 256-expert pruned Coder architecture. `ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF` compresses `Qwen3.8-Flash-Next` from 354 GB (BF16, 512 experts per layer) down to **58.4 GB** by combining: 1. **Structured Expert Pruning ($512 \rightarrow 256$ experts per layer):** Selects the 256 experts specialized for software engineering, coding, agentic tool calling, and vision. 2. **GSQ (Gumbel-Softmax Quantization) + RCO (Riemannian Co-design Search):** Assigns optimal mixed-precision GGUF quantization types across individual tensors while storing the retained weights at `~3.5 bits` (`IQ3_S`-equivalent fidelity, labeled `IQ1_M` for its `1.89` effective bits per parameter relative to the unpruned 512-expert model). --- Because this is an ultra-low-bit MoE model (`IQ1_M` effective / `IQ3_S` retained weights), **avoid pure greedy decoding (`--temp 0.0` with no repetition penalty)** on repetitive C/C++ struct definitions. Use standard Qwen sampling parameters with a light repetition/presence penalty:
译文排队中 · 当前显示来源原文
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗SCAIL-2-GGUF
AbirayThis repository contains GGUF quantizations of **SCAIL-2**, the cutting-edge end-to-end controlled character animation and video motion-transfer model built on the Wan 2.1 14B architecture by zai-org. These weights are specifically optimized to execute the heavy SCAIL-2 Diffusion Transformer (DiT) inside ComfyUI at a fraction of the native FP16/FP8 VRAM overhead. 1. **Required Loader:** Install city96's ComfyUI-GGUF extension. 2. **Node Placement:** Use the `Unet Loader (GGUF)` node. 3. **File Path:** Download your preferred quant from this repository and drop it into: ComfyUI/models/unet/ ---
译文排队中 · 当前显示来源原文
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Shieldstral-1.0-3B-GGUF
Abiray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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Sulphur-2-base-GGUF
Abiray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。
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗This repository contains **GGUF-quantized versions** of the LightX2V Distilled Wan2.2 14B Image-to-Video Model. By quantizing the ultra-fast 4-step distilled models into the GGUF format, this repository allows for drastically reduced VRAM/RAM requirements while maintaining near real-time, high-performance video generation. We provide quantizations ranging from heavily compressed (Q3) to near-lossless (Q8) to fit your specific memory and quality requirements. Both **High Noise** and **Low Noise** versions are available.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗ZAYA1-8B-GGUF
Abiray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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗t5-base-gguf
Able2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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lfm3-2b-omni-abliter8-gguf
abliter8-ai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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗lfm3-2b-vl-abliter8-gguf
abliter8-ai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
输入 文本 · 图像→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
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。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
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。
开放权重，就代表可以免费商用吗？+
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。
排行榜第一，就是最适合我的模型吗？+
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。