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
84,838 款模型档案13099 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 84838

为你发现值得关注的模型

gpt-2-tamil

abinayam

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 ↗
来源 / 文档 ↗

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

分类待补充
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 ↗
来源 / 文档 ↗

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。

分类待补充
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 ↗
来源 / 文档 ↗

**A highly optimized, consumer-hardware-friendly GGUF quantization of TenStrip's 10Eros-Max Hybrid Beta 5.** Choose the quant that best matches your GPU. *(Note: You will also need VRAM overhead for the Qwen3-VL Text Encoder, Video VAE, and Audio VAE).* These GGUFs were engineered for maximum compatibility. To bypass architecture-checking limitations in current loaders, **the architecture header has been spoofed as `"wan"`**.

译文排队中 · 当前显示来源原文

分类待补充
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 ↗
来源 / 文档 ↗

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

分类待补充
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 ↗
来源 / 文档 ↗

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

分类待补充
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 ↗
来源 / 文档 ↗

High-performance **GGUF quantizations** of TenStrip's 10Eros-Max Turbo Hybrid Beta 5, a fine-tuned, step-distilled video-and-audio model built on the **MiniMax H3** DiT architecture. These quantizations compress the original **40.2 GB FP16/BF16** weights down to **8.9 GB – 16.7 GB**, enabling fast local inference on consumer and prosumer GPUs inside ComfyUI without degrading motion dynamics or facial detail. All quants were compiled with custom **1D tensor shielding** and **K-quant divisibility folding** using patched `llama.cpp` and `ComfyUI-GGUF`.

译文排队中 · 当前显示来源原文

分类待补充
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 ↗
来源 / 文档 ↗

This repository contains GGUF weights for Anima-base-v1.0, a 2B parameter diffusion model based on the **NVIDIA Cosmos** architecture. These weights have been quantized using a specialized pipeline to ensure maximum compatibility and image quality on consumer hardware. To ensure the highest possible quality and avoid the "BF16 noise bug" common in diffusion quantization, the following steps were taken: 1. **FP32 Casting:** The original BF16 `safetensors` were cast to `FP32` before conversion. 2. **Architecture Patching:** Used a patched version of `llama.cpp` (based on build `b3962`) with the `city96` diffusion patch to support the `cosmos` architecture. 3. **Precision Preservation:** Sensitive layers (normalizations and biases) were kept in `F32` to prevent color banding and generation artifacts.

译文排队中 · 当前显示来源原文

输入 文本→ 输出 图像
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 ↗

Artemis-31B-v1.2 is a fine-tuned, unaligned creative writing and roleplay model built on Google's **Gemma 4 31B** base architecture. It is specifically calibrated for literary depth, psychological nuance, long-horizon scene continuity, and multi-turn roleplay. Artemis-31B uses the **Gemma 4 Chat Template** and natively supports both **Thinking (Reasoning Scratchpad)** and **Direct Storytelling** operational modes. Trigger the reasoning planner by embedding ` ` into the prompt. The model will plan character motivations, spatial distance, and scene tone in a scratchpad before generating the visible narrative.

译文排队中 · 当前显示来源原文

分类待补充
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 ↗
来源 / 文档 ↗

This repository provides **two distinct formats** depending on your runtime: 1. **🔥 NEW: Unified Single-File Hybrid GGUFs (`*_vision_q8_0.gguf`)** — Combines the K-quantized LLM backbone (`Q4_K_M` / `Q5_K_M`) and the `Q8_0` Vision Tower + DeepStack Mergers + 5D `Conv3d` shape metadata (`comfy.gguf.orig_shape`) inside a **single file**. 2. **Split LLM + Standalone `mmproj` GGUFs** — Standard two-file format for **llama.cpp**, **llama-server**, **Ollama**, and split VLM loaders. *Contains both the Language Backbone (`blk.*`) and Vision Tower (`model.visual.*`) in a single GGUF file.* 1. Download either `qwen3vl_8b_q4_k_m_vision_q8_0.gguf` or `qwen3vl_8b_q5_k_m_vision_q8_0.gguf` and place it into:

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 ↗
来源 / 文档 ↗

This repository provides a **standalone, weight-baked abliterated (uncensored) GGUF build** of `ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF` (`IQ2_XXS`, 2.00 bpw) using the rank-1 EN+RU refusal-direction abliteration from `AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF`. - **Zero LoRA Required at Runtime:** All 86 abliterated residual-writing tensors are baked directly into the 4 GGUF backbone shards. No `--lora` adapter flags are needed. - **Same Size as Original (`138.58 GB` vs. `138.24 GB`):** Adds only `+0.34 GB` (`+0.25%`) across the entire 4-shard 763B model. - **100% GSQ-RCO Intelligence Preserved:** All **28 1-bit `IQ1_M` GSQ-calibrated routed-expert layers** and both **`blk.{1,14}.engram_wkv.weight` (`Q5_K`)** projections from ISTA-DASLab are preserved 100% untouched, while all **80 dense residual writers** (`blk.{0..39}.attn_output_b.weight` in `Q6_K` and `blk.{0..39}.ffn_down_shexp.weight` in `Q8_0`/`Q5_K`) plus the **6 exact-type 2-bit routed-expert layers** (`blk.7, 8, 10, 18` in `IQ2_XXS` and `blk.33, 39` in `IQ2_XS`) carry the full refusal-direction removal. > **Important:** Like the upstream ISTA-DASLab release, this 4-shard backbone pairs with the shared **`DeepSeek-V4.1-Flash-Engram-IQ4_NL.gguf`** (`110.60 GB`) lookup file from `ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF`. Place all 4 shards and the Engram file in the same directory.

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 ↗
来源 / 文档 ↗

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 ↗
来源 / 文档 ↗

High-precision **GGUF quantizations** of **FastVideo/FastH3-Omni-Comfy** (`fasth3_omniref_8step_pruned_bf16.safetensors`), the **8-step consistency-distilled Omni-Reference (`Ref2VA`)** model built on **MiniMax-H3** by FastVideo (Hao AI Lab) in collaboration with Nuva Lab and Reactor. Unlike standard naive quantizations that crush timestep modulation tables and output heads into low-bit blocks, **this GGUF suite uses hybrid precision shielding** to keep critical audio/video decoding heads, 32-head PDD (Progressive Distillation) offsets, and AdaLN interpolation tables in **lossless `FP32`**, while compressing the 50-block DiT + Video Sparse Attention (`VSA`) backbone for consumer RTX GPUs. All files are converted from the **44.24 GB Pruned BF16** checkpoint (`FastVideo/FastH3-Omni-Comfy`) compatibility with `city96/ComfyUI-GGUF`.

译文排队中 · 当前显示来源原文

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 ↗
来源 / 文档 ↗

GGUF quantizations of Black Forest Labs' FLUX 3 Image Klein (16-step distilled checkpoint) for use with ComfyUI-GGUF. A pre-configured Text-to-Image (T2I) workflow is included in this repository: * **Download Workflow:** image_flux3_klein_distilled_t2i_GGUF.json A pre-configured Image-edit (I2I) workflow is included in this repository: * **Download Workflow:** image_flux3_klein_distilled_image_edit_GGUF.json

译文排队中 · 当前显示来源原文

输入 文本→ 输出 图像
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 ↗