Search FoxAI
AI Models 84759
- Qwen3-30B-A3B-Instruct-2507-GGUF↗
ubergarm
- Qwen2.5-VL-72B-Instruct-GGUF↗
unsloth
In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL. We extend dynamic resolution to the temporal dimension by adopting dynamic FPS sampling, enabling the model to comprehend videos at various sampling rates. Accordingly, we update mRoPE in the time dimension with IDs and absolute time alignment, enabling the model to learn temporal sequence and speed, and ultimately acquire the ability to pinpoint specific moments. We enhance both training and inference speeds by strategically implementing window attention into the ViT. The ViT architecture is further optimized with SwiGLU and RMSNorm, aligning it with the structure of the Qwen2.5 LLM.
- Trinity-Large-Preview-GGUF↗
unsloth
- SauerkrautLM-ColQwen3-2b-v0.1↗
VAGOsolutions
SauerkrautLM-ColQwen3-2b-v0.1 achieves **90.24 NDCG@5** on ViDoRe v1, making it the **#1 in the Medium (1-3B) category** among 128-dim models - a significant **+1.01 improvement** over the baseline ColQwen2-v1.0. Traditional OCR-based retrieval **loses layout, tables, and visual context**. Our visual approach: - ✅ **No OCR errors** - Direct visual understanding - ✅ **Layout-aware** - Understands tables, forms, charts - ✅ **End-to-end** - Single model, no pipeline complexity **ViDoRe v1 Tasks:** | Task | Score | |------|-------| | ArxivQA | 91.24 | | DocVQA | 65.06 | | InfoVQA | 93.14 | | ShiftProject | 88.74 | | SyntheticDocQA-AI | 99.63 | | SyntheticDocQA-Energy | 96.91 | | SyntheticDocQA-Gov | 96.08 | | SyntheticDocQA-Health | 99.26 | | TabFQuAD | 90.32 | | TATDQA | 82.06 |
- Fin-Retriever-base↗
valuesimplex-ai-lab
- Qwen3.8-27B-GGUF↗
vaultai
- Veyra2-Blueberry-10M-Base↗
veyra-ai
- qwen3.8_27b-uncensored-ninfer↗
xidisdg
本仓库由 xidisdg 分享，提供 Qwen3.8-27B 系列的 **NInfer 原生 `.ninfer` 模型文件**，包括 NVFP4、NVFP4Full 及 DFlash2 变体，分为 **原始版本**（适配特定构建）和 **V3 版本**（适配最新版 NInfer）。 > **下载前注意：** 各文件是供选择的不同版本，不是需要一起下载的分片。名称中的 `uncensored` 是发布文件的版本标识，不代表已经完成拒答率、安全性或能力评测。V3 版本适配最新版 NInfer，原始版本适配特定构建版本。 V3 文件针对 NInfer 最新版本重新制作，**仅适用于最新版 NInfer**。旧版运行时无法加载 V3 文件；反过来，V3 运行时通常也无法加载原始版本文件。请确认你的 NInfer 版本后再选择对应文件。
- MiMo-V2.6-Flash-RL-GGUF↗
YanissAmz
A single-quant GGUF of XiaomiMiMo/MiMo-V2.6-Flash-RL (309B total / 15B active, 256 experts, top-8), 2.76 bits per weight on average, sized for machines with ~110 GB of free RAM/VRAM: 128 GB unified-memory systems (AMD Ryzen AI Max+ 395 / Strix Halo, Apple Silicon 128 GB, DGX Spark), multi-GPU rigs, or CPU + GPU offload. It is a standard GGUF: any llama.cpp build and backend (CUDA, ROCm/HIP, Vulkan, Metal, CPU) runs it. Loads and generates on stock llama.cpp (tested: master of 2026-09-23, CPU build). The speeds above are one example machine (AMD Ryzen AI Max+ 395, Radeon 8060S, llama.cpp Vulkan build); other hardware will differ. `-ub 2048` matters for MoE prefill (Strix Halo example: 193 tok/s at the default `-ub 512`, 310 tok/s at 2048).
- GLM-5.3-Flash↗
Z AI