AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI NEWS · 模型情报站发现能力边界，让每一次选择更有依据 ↗基础档案先收录 · 缺失资料持续补齐
THE AI MODEL DIRECTORY 模型探索，从这里开始

找到适合你的 AI 模型。

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。

热门探索
84,991 款模型档案13202 家厂商 / 发布者45 个能力分类465 款有可比报价 · 30 款有公开评测
T文本生成▧图像生成▷视频生成⌘代码生成◖语音合成♫音乐生成⬡3D 建模▤文档分析
DISCOVER & COMPARE

探索 AI 模型 271

为你发现值得关注的模型

- **Model Architecture:** MuseGlimmerForConditionalGeneration - **Input:** Text / Image - **Output:** Text - **Model Optimizations:** - **Weight quantization:** FP8 - **Activation quantization:** FP8 - **Release Date:** 2026-08-10 - **Version:** 1.0 - **Model Developers:** RedHatAI This model is a quantized version of meta-models/Muse-Glimmer-30B. This model was obtained by quantizing the weights and activations of meta-models/Muse-Glimmer-30B to FP8 (W8A8 block) data type, ready for inference with vLLM.

译文排队中 · 当前显示来源原文

视觉问答
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 ↗
来源 / 文档 ↗

- **Model Architecture:** NemotronHForCausalLM - **Input:** Text - **Output:** Text - **Model Optimizations:** - **Weight quantization:** FP8 - **Activation quantization:** FP8 - **Release Date:** 2026-08-13 - **Version:** 1.0 - **Model Developers:** RedHatAI This model is a quantized version of nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16. This model was obtained by quantizing the weights and activations of nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 to the FP8 data type, using a per-tensor static scheme. This reduces the number of bits per parameter from 16 to 8, cutting GPU memory and disk requirements by approximately 50% and roughly doubling matrix-multiply compute throughput on FP8-capable hardware. Only the weights and activations of the linear operators within the transformer blocks are quantized, using LLM Compressor.

译文排队中 · 当前显示来源原文

文本生成开放权重
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 ↗
来源 / 文档 ↗

Nemotron-Nano-3-30B-A3B-FP8 is a quantized version of Nemotron-Nano-3-30B-A3B and is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be configured through a flag in the chat template. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks. The model employs a hybrid Mixture-of-Experts (MoE) architecture, consisting of 23 Mamba-2 and MoE layers, along with 6 Attention layers. Each MoE layer includes 128 experts plus 1 shared expert, with 6 experts activated per token. The model has 3.5B active parameters and 30B parameters in total. The supported languages include: English, German, Spanish, French, Italian, and Japanese. Improved using Qwen.

译文排队中 · 当前显示来源原文

文本生成
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 ↗
来源 / 文档 ↗

This model was obtained by quantizing activation and weights of phi-4 to FP8 data type. This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x). Weight quantization also reduces disk size requirements by approximately 50%. Only weights and activations of the linear operators within transformers blocks are quantized. Weights are quantized with a symmetric static per-channel scheme, whereas activations are quantized with a symmetric dynamic per-token scheme. The llm-compressor library is used for quantization. The model was evaluated on the OpenLLM leaderboard tasks (version 1) with the lm-evaluation-harness and the vLLM engine, using the following command:

译文排队中 · 当前显示来源原文

文本生成
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 ↗
来源 / 文档 ↗
COST EXPLORER

好模型，也要算好成本。

费用分析

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

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

选型与常见问题
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。

AI NEWS · 从信息到选择

资讯看趋势，工具提效率，模型筑可能。

探索 AI 资讯 ↗发现 AI 工具 ↗