MiniCPM5-2B-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 ↗DISCOVER & COMPARE
探索 AI 模型 84838
This repository hosts quantized GGUF checkpoints based on **openbmb/MiniCPM5-2B**, implementing the directional refusal ablation methodology showcased in insraq/MiniCPM5-2B-heretic-abliterated via **Heretic v1.4.0**. These builds are packaged for local on-device inference using llama.cpp, Ollama, LM Studio, Jan, and standard GGUF executors. Directional ablation neutralizes the refusal reflex across the residual stream and MLP projections while preserving the primary base model's mathematical, coding, and multi-step reasoning performance.
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 ↗MiniMax-H3-GGUF
AbirayThis repository (`Abiray/MiniMax-H3-GGUF`) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. --- If you are looking for a smaller model with the same great quality that fits better on consumer-tier GPUs, please check out the **MiniMax-H3-Pruned-GGUF** repository. The pruned architecture is compressed down to 8.9 GB – 21.6 GB, bringing MiniMax H3 execution directly to consumer hardware. **Available Pruned Quants:** | Bit Size | Quantization Type | File Size | | :--- | :--- | :--- | | **3-bit** | `Q3_K_M` | 8.9 GB | | **4-bit** | `Q4_K_S`, `Q4_K_M` | 11.6 GB | | **5-bit** | `Q5_K_S`, `Q5_K_M` | 14.1 GB | | **6-bit** | `Q6_K` | 16.7 GB | | **8-bit** | `Q8_0` | 21.6 GB | --- This repository includes quantized versions of both the `FL2VA` (First-and-last-frame mode) and `Ref2VA` (Omni-reference mode) base models. * **FL2VA Models:** * `MiniMax-H3-FL2VA-Q3_K_M.gguf` (15.6 GB) * `MiniMax-H3-FL2VA-Q3_K_S.gguf` (15.6 GB) * `MiniMax-H3-FL2VA-Q4_0.gguf` (18.6 GB) * `MiniMax-H3-FL2VA-Q4_K_M.gguf` (19.9 GB) * `MiniMax-H3-FL2VA-Q4_K_S.gguf` (19.9 GB) * `MiniMax-H3-FL2VA-Q5_0.gguf` (22.8 GB) * `MiniMax-H3-FL2VA-Q5_K_M.gguf` (23.9 GB) * `MiniMax-H3-FL2VA-Q5_K_S.gguf` (23.9 GB) * `MiniMax-H3-FL2VA-Q6_K.gguf` (28.2 GB) * `MiniMax-H3-FL2VA-Q8_0.gguf` (36 GB) * **Ref2VA Models:** * `MiniMax-H3-Ref2VA-Q3_K_M.gguf` (15.6 GB) * `MiniMax-H3-Ref2VA-Q3_K_S.gguf` (15.6 GB) * `MiniMax-H3-Ref2VA-Q4_0.gguf` (18.6 GB) * `MiniMax-H3-Ref2VA-Q4_K_M.gguf` (19.9 GB) * `MiniMax-H3-Ref2VA-Q4_K_S.gguf` (19.9 GB) * `MiniMax-H3-Ref2VA-Q5_0.gguf` (22.8 GB) * `MiniMax-H3-Ref2VA-Q5_K_M.gguf` (23.9 GB) * `MiniMax-H3-Ref2VA-Q5_K_S.gguf` (23.9 GB) * `MiniMax-H3-Ref2VA-Q6_K.gguf` (28.2 GB) * `MiniMax-H3-Ref2VA-Q8_0.gguf` (36 GB) * `qwen3vl_32b_minimax_h3_int4_convrot.safetensors` (15 GB) * `qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors` (27.1 GB) * `qwen3vl_32b_minimax_h3-Q4_K_M.gguf` (14.6 GB) * `minimax_h3_audio_vae_fp32.safetensors` (605 MB) * `minimax_h3_video_vae_fp16.safetensors` (5.21 GB) * **H3-Base-FL2VA:** First-and-last-frame mode. Supports zero, one, or two input images. * No image input: T
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 ↗This repository is a community-compiled collection of quantized and pruned weights for **MiniMax H3 (Hailuo 3.0)**, optimized for local inference environments like ComfyUI. By unifying various quantization formats (INT4, INT8, Mixed, and NVFP4) into a single structured repository, this hub makes it easier for users with consumer GPUs (16GB - 24GB VRAM) to experiment with MiniMax H3's powerful omni-modal text/image/audio-to-video generation capabilities. If you are new to local generation and aren't sure what to download, use this guide based on your graphics card.
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 ↗MiniMax-H3-Pruned-GGUF
AbirayThis repository (`Abiray/MiniMax-H3-Pruned-GGUF`) provides pruned and quantized GGUF weights for the **MiniMax H3** omni-modal generative model. MiniMax H3 is designed for unified multimodal context processing, capable of generating synchronized high-definition video and 32 kHz stereo audio from text, image, audio, and video inputs. * **VRAM Efficiency:** Pruned architecture compressed down to **8.9 GB – 21.6 GB**, bringing MiniMax H3 execution to consumer-tier GPUs. * **Synchronized Omni-Modal Output:** Simultaneous generation of video (24 FPS) and native stereo audio (32 kHz). * **Native ComfyUI Support:** Directly compatible with standard `ComfyUI-GGUF` workflows using the native MiniMax backend. * **Dual Pipeline Variants:** Full quant suites for both `FL2VA` (First/Last Frame) and `Ref2VA` (Omni-Reference) modes. > **Note:** For optimal performance, **Q4_K_M** is recommended for 16 GB GPUs, while **Q5_K_M** is recommended for GPUs with 24 GB VRAM.
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 hybrid model fuses the crisp visual quality, motion dynamics, and clean audio of **FL2VA** with the persistent multi-image character conditioning of **Ref2VA** using a **rank-1024 delta weight merge ($\Delta W_{r=1024}$)** on the pruned 20.1B parameter MiniMax-H3 architecture. With these GGUFs, you can now run reference-conditioned MiniMax-H3 locally on consumer GPUs (16 GB – 24 GB VRAM) with minimal quality loss. Place the downloaded `.gguf` file into: ComfyUI/models/diffusion_models/ *(or `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 ↗GGUF quantized versions of **WarmBloodAban/Minimax-h3_Singularity**, a community fine-tune of MiniMax H3 specialized in enhanced visual fidelity — HDR clarity, distant-face restoration, cleaner skin, stronger action motion, and improved VFX. These quantizations reduce VRAM requirements for use with ComfyUI, enabling local inference on consumer GPUs. Place the downloaded `.gguf` file in your ComfyUI `models/unet/` directory (or `models/diffusion_models/` depending on your ComfyUI-GGUF fork). You will also need the following components: For accelerated generation, you can optionally pair this model with the **minimax_h3_ref2v_turbo_4step_v0.1** LoRA, which enables 4-step fast inference.
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 ↗Pruned and optimized `.safetensors` versions of WarmBloodAban/Minimax-H3 Singularity, formatted for native ComfyUI custom nodes (such as `comfyui-mixed-quantizer` and native INT8 loaders). 1. Place your chosen `.safetensors` file into your ComfyUI models folder: `ComfyUI/models/diffusion_models/` 2. Load the model using your preferred native ComfyUI loader or mixed-quantizer custom nodes. 3. Pair it with the Qwen3-VL text encoder and MiniMax-H3 Video + Audio VAEs.
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 ↗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 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 ↗It is designed to dramatically accelerate both video and audio generation for the MiniMax-H3 model. By using this adapter, you can drastically cut down the required sampling steps while still generating native, synchronized 32kHz stereo audio alongside your video. The initial release of this LoRA required a standalone custom Python script because standard ComfyUI samplers struggled to handle the dual-schedule (video + audio) mechanics without blowing out the audio track. **This specific `.safetensors` file has been structurally pruned and reformatted so it works seamlessly inside standard ComfyUI workflows.** You can load it using a standard `Load LoRA` node. It is optimized to run alongside the pruned or curve-form MiniMax-H3 checkpoints designed for ComfyUI.
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 ↗MiniMax-Music3-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 音频
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 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 ↗Muse-Glimmer-30B-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 · 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 ↗Nanbeige4.2-3B-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。
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 ↗Nemotron-3-Embed-8B-GGUF
AbirayWelcome to the **GGUF** repository for NVIDIA's Nemotron-3-Embed-8B-BF16. This model is a state-of-the-art, 8-billion parameter multilingual text embedding model optimized for Retrieval-Augmented Generation (RAG), semantic search, and cross-lingual retrieval workflows. It achieved **#1 on the multilingual RTEB leaderboard** (as of July 2026). By converting the model to **GGUF (GPT-Generated Unified Format)**, you can run enterprise-grade retrieval locally on consumer hardware (CPUs and GPUs) using tools like `llama.cpp`, `Ollama`, or `LM Studio`.
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 ↗OUI-1-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 ↗OvisOCR2-GGUF
AbirayThis repository contains GGUF format quantizations of **OvisOCR2**, a compact 0.8B end-to-end model for page-level document parsing. The original model was developed by **ATH-MaaS** by post-training `Qwen3.5-0.8B` to parse full document pages directly into clean Markdown (including LaTeX formulas, HTML tables, and layout components). OvisOCR2 establishes a new state-of-the-art for compact document understanding, scoring **96.58** on OmniDocBench v1.6 and outperforming traditional, multi-stage layout analysis pipelines. *Note: Because OvisOCR2 is a vision-language model, you **must** download one of these image processing units alongside your choice of the text models listed above.*
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 ↗Qwen-Image-2.1-GGUF
AbirayThis repository provides quantized **GGUF** checkpoints for Qwen/Qwen-Image-2.1, optimized for low-VRAM inference in **ComfyUI** using the ComfyUI-GGUF custom node. Quantizing the diffusion transformer drastically reduces memory pressure during generation while preserving sharp detail, composition, and prompt alignment. To run these models in ComfyUI, you will need the matching text encoders and VAE:
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 ↗Quantized GGUF weights for Alibaba's official **Qwen-Image-2.1-Turbo** distilled diffusion model. These checkpoints enable lightning-fast text-to-image and image-editing generation in ComfyUI at a fraction of the native VRAM requirement, taking full advantage of 4–8 step Turbo sampling. All models were converted using `ComfyUI-GGUF` tools and quantized using a patched multi-threaded `llama-quantize` build natively supporting the 297-tensor `qwen_image` architecture.
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 ↗This repository contains optimized community **GGUF quantizations** of Viggle/Qwen-Image-2.1-viggle-turbo, an official 4-step distilled student model of Qwen-Image-2.1 trained by Viggle using **Distribution Matching Distillation (DMD)**. These files were converted directly from the official full transformer weights (`transformer/diffusion_pytorch_model.safetensors`), allowing you to run near-instant 4-step image generation and image editing natively inside **ComfyUI** without needing to stack external LoRAs. Because this model is distilled with DMD, **it requires specific inference parameters**. Using standard diffusion parameters will degrade image quality or cause visual burn 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 ↗This repository contains standalone **GGUF quantizations** of Alibaba's **Qwen-Image-2.1**, natively fused with **Viggle's v0.2.1 6-Step Turbo LoRA (Rank 256)**. By permanently fusing the high-rank distilled velocity field in FP32 prior to quantization, these checkpoints run full text-to-image generation in **just 6 steps with zero CFG**, yielding a **~4.5× speedup** while running entirely within ComfyUI's native GGUF loader.
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 ↗This repository provides standalone **GGUF quantizations** of Alibaba's **Qwen-Image-2.1**, natively fused with **Viggle's v0.3 6-Step Turbo LoRA (Rank 256 / Alpha 256)**. By baking the distilled velocity field permanently into the base DiT in high-precision **FP32** prior to quantization, these checkpoints eliminate runtime LoRA overhead, avoid stock runtime merge degradation (~30% update precision loss in stock BF16 loaders), and run at full speed inside ComfyUI's native GGUF loader in **just 6 steps with zero CFG**. > **Note on Single-File GGUF:** Because the v0.3 LoRA is already fused into the model, you do not need to load or chain any LoRA nodes in ComfyUI. Load the GGUF directly into your sampler pipeline.
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 ↗Qwen3.5-2B-heretic-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 · 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。
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 ↗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。