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。
探索 AI 模型 85003
A **compressed-tensors NVFP4 W4A4** release of heretic-org/Qwen3.8-27B-heretic-ara with the original **BF16 vision/video tower** and all **15 native BF16 MTP tensors** retained and runtime-validated on one RTX 5090. > **Release artifact:** this repository contains the converted `nvfp4-pack-quantized` checkpoint. The raw ModelOpt export was an intermediate artifact. Conversion to compressed-tensors is required for the tested Qwen3.8 multimodal + MTP vLLM path. Primary runtime: **vLLM's Qwen3.8 CUDA 13 build**. The packed NVFP4 weights, multimodal path, and native MTP drafter were validated with the pinned image below. Hugging Face may display an automatic `8-bit` badge because two FP4 values are physically packed in each U8 storage element; the quantization is NVFP4 W4A4.
译文排队中 · 当前显示来源原文
A complete NInfer artifact derived from huihui-ai/Huihui-Qwen3.8-27B-abliterated revision `d42ca8978c5a66e92c3446d46e8adfe03ef692ff`. The artifact combines NInfer's fixed **FP8 + NVFP4** Qwen3.8 allocation with same-source Huihui BF16 norms, embeddings, vision tower, and MTP tensors. No official Qwen or unrelated behavioral checkpoint supplies model weights. The v3 file preserves all 1,118 original tensor encodings and the entire original payload byte-for-byte. It appends the maintained Qwen3.8 chat template and adds the v3 directory and bindings. This is a container/template update, not a new quantization. It does not add an indexed proposal head or DFlash2 weights; omit `--lm-head-draft` and `--spec dflash2`.
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
Qwen3.8-27B-Uncensored-exl3-4bpw
Lygodactylus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
Qwen3.8-27B-Uncensored-exl3-5bpw
Lygodactylus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
Qwen3.8-27B-Uncensored-exl3-8bpw
Lygodactylus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
Qwen3.8-Flash-Next-Uncensored-exl3-3bpw
Lygodactylus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
Qwen3.8-Flash-Next-Uncensored-exl3-4bpw
Lygodactylus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
MiniMax-M3.1-Flash-GGUF
LyJonathanQuantized GGUF copies of MiniMax-M3.1-Flash for Sparsa. Most of these files do not load in stock llama.cpp, LM Studio or Ollama; use Sparsa, latest release v0.1.3. Each tier is a folder of 13 parts; point Sparsa at the folder. Quality is measured against an FP32 reference of the original weights, 6 short prompts, 679 positions: **top-1** is how often the tier's top next token matches the reference (higher is better), **KL64** is divergence over the reference's top 64 tokens (lower is better). `IQ2_XS` is only measured in patched llama.cpp on a harder eight-prompt set (top-1 46.8 %, KL 1.92; `IQ2_XS-D3` on that set: 53.8 %, 1.58), so the number is not comparable with the table. `Sparsa only` means upstream llama.cpp cannot read those expert types. The experts were trained as 4-bit (NVFP4), so the 1-2-bit tiers are degraded, and one hard code prompt pulls every mean down.
译文排队中 · 当前显示来源原文
AAM_AnyLora_AnimeMix
Lykon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。
基础资料已收录 · 缺失资料后续补充
AAM_XL_AnimeMix
Lykon`Lykon/AAM_XL_AnimeMix` is a Stable Diffusion model that has been fine-tuned on stabilityai/stable-diffusion-xl-base-1.0.
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
AbsoluteReality
LykonConsider supporting me on Patreon or buy me a coffee - https://www.patreon.com/Lykon275 - https://snipfeed.co/lykon You can run this model on: - https://huggingface.co/spaces/Lykon/DreamShaper-webui - Mage.space, sinkin.ai and many more
译文排队中 · 当前显示来源原文
AnimePastelDream
Lykon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
AnyLoRA
Lykon`lykon/AnyLoRA` is a Stable Diffusion model that has been fine-tuned on runwayml/stable-diffusion-v1-5. Please consider supporting me: - on Patreon - or buy me a coffee For more general information on how to run text-to-image models with 🧨 Diffusers, see the docs.
译文排队中 · 当前显示来源原文
DreamShaper
LykonAlso please support by giving 5 stars and a heart, which will notify new updates. Please consider supporting me on Patreon or buy me a coffee - https://www.patreon.com/Lykon275 - https://snipfeed.co/lykon You can run this model on: - https://huggingface.co/spaces/Lykon/DreamShaper-webui - Mage.space, sinkin.ai and more
译文排队中 · 当前显示来源原文
dreamshaper-7
Lykon`lykon/dreamshaper-7` is a Stable Diffusion model that has been fine-tuned on runwayml/stable-diffusion-v1-5. Please consider supporting me: - on Patreon - or buy me a coffee For more general information on how to run text-to-image models with 🧨 Diffusers, see the docs.
译文排队中 · 当前显示来源原文
dreamshaper-8
Lykon`lykon/dreamshaper-8` is a Stable Diffusion model that has been fine-tuned on runwayml/stable-diffusion-v1-5. Please consider supporting me: - on Patreon - or buy me a coffee For more general information on how to run text-to-image models with 🧨 Diffusers, see the docs.
译文排队中 · 当前显示来源原文
`lykon-models/dreamshaper-8-inpainting` is a Stable Diffusion Inpainting model that has been fine-tuned on runwayml/stable-diffusion-inpainting.
译文排队中 · 当前显示来源原文
dreamshaper-8-lcm
Lykon`lykon/dreamshaper-8-lcm` is a Stable Diffusion model that has been fine-tuned on runwayml/stable-diffusion-v1-5. Please consider supporting me: - on Patreon - or buy me a coffee For more general information on how to run text-to-image models with 🧨 Diffusers, see the docs.
译文排队中 · 当前显示来源原文
dreamshaper-xl-1-0
Lykon`lykon-models/dreamshaper-xl-1-0` is a Stable Diffusion model that has been fine-tuned on stabilityai/stable-diffusion-xl-base-1.0.
译文排队中 · 当前显示来源原文
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。
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。
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。
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。