Search FoxAI
AI Models 2119
- Nous-Hermes-Llama2-70B-GGUF↗
TheBloke
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible. The creator of the source model has listed its license as `['mit']`, and this quantization has therefore used that same license. As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
- flux-3-image-klein-base-GGUF↗
unsloth
This is a GGUF quantized version of FLUX 3 Image Klein Base by Black Forest Labs, the 5.6B image transformer (undistilled checkpoint, 50 steps with CFG 3.5) for text to image and image editing. unsloth/flux-3-image-klein-base-GGUF uses Unsloth Dynamic 2.0 methodology: the `UD-` files are mixed precision, with every layer's type chosen from a measured sensitivity scan, and they beat the uniform files at the same size. - Loads in diffusers through `Flux3Transformer2DModel.from_single_file(..., quantization_config=GGUFQuantizationConfig(...))`. Also loads in Unsloth Desktop. - Tensor names follow the original Black Forest Labs checkpoint layout. The text encoder (Qwen3-VL-4B-Instruct) and the VAE are unchanged and identical to the distilled release; take them from black-forest-labs/flux-3-image-klein-base or black-forest-labs/flux-3-image-klein. **Recommended:** `UD-Q4_K_XL` (3.93 GB) for most GPUs: LPIPS 0.057 against 0.077 for `Q4_K_M`. `UD-Q5_K_XL` (4.48 GB) is closer to bf16 than `Q6_K`. For output closest to bf16 use `Q8_0`; on small cards use `UD-Q2_K_XL` (2.62 GB). LPIPS (alex, lower is better) and SSIM against the bf16 transformer, same prompt, seed, noise and text encoder, 50 steps at CFG 3.5, over 19 renders: 8 held-out prompts at 1024x1024 plus 11 text-to-image and editing cases (single and multi-reference). A repeated bf16 render scores 0, so the numbers measure only the quantization.
- distilbert-base-uncased↗
distilbert
This model is a distilled version of the BERT base model. It was introduced in this paper. The code for the distillation process can be found here. This model is uncased: it does not make a difference between english and English. DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts using the BERT base model. More precisely, it was pretrained with three objectives: This way, the model learns the same inner representation of the English language than its teacher model, while being faster for inference or downstream tasks.
- sam2.1-hiera-large↗
facebook
Repository for SAM 2: Segment Anything in Images and Videos, a foundation model towards solving promptable visual segmentation in images and videos from FAIR. See the SAM 2 paper for more information. The official code is publicly release in this repo. Refer to the demo notebooks for more details.
- kosamasi↗
kosamasi
- H3-Turbo-Neat↗
moe-kill
A practical family of low-step MiniMax H3 LoRAs for both video and still-image generation, focused on image quality, motion, acting, prompt stability, audio, and real-world usability. > **Important:** Neat Classic and Neat Prime use different workflows and sampling setups. > Do not mix their sampler nodes or recommended settings. 它最大的实用价值之一，是可以让 **H3 自己为 H3 制作参考图**：先在相同模型审美空间中完成角色、服装、灯光、场景与镜头设计，再将参考图直接回喂给 H3 做视频。相比使用外部生图模型，这种同源参考图与 H3 的色彩、人物塑形和材质逻辑天然一致，能够显著减少风格不匹配和参考图“进视频后变味”的问题。
- MiniCPM5-1B-Base↗
openbmb
MiniCPM Tech Report | MiniCPM Wiki(Chinese) | GitHub Repo | UltraData | MiniCPM Desk Pet | Online Demo We are releasing **MiniCPM5-1B**, the first model in the **MiniCPM5** series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA. 🏆 **1B-class open-source SOTA**: compared with strong open-source models in the same size class, MiniCPM5-1B reaches SOTA within this comparison set. Its advantage is most visible in agentic tool use, code generation, and difficult reasoning.
- resnet101.a1h_in1k↗
timm
This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample Recipe details: * Based on ResNet Strikes Back `A1` recipe * LAMB optimizer * Stronger dropout, stochastic depth, and RandAugment than paper `A1` recipe * Cosine LR schedule with warmup
- FLUX.2-klein-4B-FP8↗
unsloth
This is an FP8 / INT8 quantized version of FLUX.2-klein-4B. - Optimized for efficient inference with reduced memory footprint. Same-seed LPIPS vs the bf16 model (lower is better): 0.123 INT8, 0.104 FP8. The FLUX.2 [klein] model family are our fastest image models to date. FLUX.2 [klein] unifies generation and editing in a single compact architecture, **delivering state-of-the-art quality with end-to-end inference in as low as under a second**. Built for applications that require real-time image generation without sacrificing quality, and runs on consumer hardware, with as little as 13GB VRAM. FLUX.2 [klein] 4B is a 4 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.
- asr-wav2vec2-ctc-french↗
bofenghuang
This model is a fine-tuned version of LeBenchmark/wav2vec2-FR-7K-large, trained on a composite dataset comprising of over 2200 hours of French speech audio, using the train and validation splits of Common Voice 11.0, Multilingual LibriSpeech, Voxpopuli, Multilingual TEDx, MediaSpeech, and African Accented French. When using the model make sure that your speech input is also sampled at 16Khz.