Search FoxAI

AI Models 84759

• qwen-image-2.1-comfy↗

  t8star

  This repository is a convenience mirror of **four existing Q4_K_M prompt-enhancer GGUF models and two BF16 vision projectors** for ComfyUI-Qwen-Image-Prompt-Rewrite-T8, also available in the ComfyUI Registry. The files were **not trained or quantized by T8star**. They retain their original filenames and SHA256 checksums. This is a prompt-rewriting collection, **not** the Qwen Image 2.1 image-generation diffusion model, text encoder, or VAE. 本仓库集中存放用于 ComfyUI 提示词改写节点的四个 Q4_K_M GGUF 主模型及两个 BF16 视觉组件。T8star 并非原模型训练者或量化作者。这里的权重只负责改写提示词，不能单独出图。 The original Qwen prompt-enhancer checkpoints are Qwen/Qwen-Image-2.1-PE-T2I and Qwen/Qwen-Image-2.1-PE-I2I. The Heretic GGUFs are based on pottokao/Qwen-Image-2.1-PE-T2I-Heretic and pottokao/Qwen-Image-2.1-PE-I2I-Heretic. Built with Qwen. See each source repository for its own authorship and technical details.

• Granite-4.2-8B-BE-GGUF↗

  taronaeo

• Qwen3.8-Flash-Next-MLX-oQ8-MTP↗

  TensorFold

• LLaMA2-13B-TiefighterLR-GGUF↗

  TheBloke

• autojev-27b-GGUF↗

  thomasgauthier

• Ornith-1.5-9B-heretic-GGUF↗

  Thunder13240

  **Importance-matrix GGUF quantizations of an abliterated Ornith-1.5-9B.** > ### Progressive release > > **Our upload bandwidth is limited (~1 MB/s), so the full 24-quant ladder takes many hours to transfer.** > Rather than sit on everything until the last byte lands, files are being published as they finish uploading: > > 1. `Q4_K_M` and the vision projector first - the ones most people want > 2. Then `Q8_0`, `Q6_K`, `Q5_K_M`, `IQ4_XS`, `Q4_K_S` > 3. Then the remaining low-bit quants, over the following hours > > **23 quants are built and queued.** The table below lists what is *currently live in this repo* and is regenerated as uploads > land - so if the file you want is missing, it is on its way rather than cancelled. Check back later, or watch the repo. Top-token agreement on this model looks low compared to figures you may have seen for other GGUF repos. **It is not a defect, and it is not caused by the abliteration.** The control proves it:

• MobileCLIP2-S0-OpenCLIP↗

  timm

  These weights and model card are adapted from the original Apple model at https://huggingface.co/apple/MobileCLIP2-S0. This version uses canonical OpenCLIP configs and weight naming. MobileCLIP2 was introduced in MobileCLIP2: Improving Multi-Modal Reinforced Training (TMLR August 2025 Featured ), by Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, Alexander T Toshev, Oncel Tuzel, Hadi Pouransari. * `MobileCLIP2-S4` matches the accuracy of SigLIP-SO400M/14 with 2x fewer parameters and surpasses DFN ViT-L/14 at 2.5x lower latency measured on iPhone12 Pro Max. * `MobileCLIP-S3/S4` are our new architectures trained on MobileCLIP’s training dataset, DataCompDR-1B (dashed lines). * Our smallest variant `MobileCLIP-S0` obtains similar zero-shot performance as OpenAI's ViT-B/16 model while being 4.8x faster and 2.8x smaller. * `MobileCLIP-S2` obtains better avg zero-shot performance than SigLIP's ViT-B/16 model while being 2.3x faster and 2.1x smaller, and trained with 3x less seen samples. * `MobileCLIP-B (LT)` attains zero-shot ImageNet performance of **77.2%** which is significantly better than recent works like DFN and SigLIP with similar architectures or even OpenAI's ViT-L/14@336.

• regnetx_120.pycls_in1k↗

  timm

• nk_babylm_zho_gpt2_atomic_bpe_cross_100m↗

  timorobrecht

• tiny-Qwen3ForCausalLM-Instruct-2507↗

  trl-internal-testing