Search FoxAI

AI Models 449

• gemma-3-12b-it↗

  unsloth

  Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. With instruction-tuned models, you need to use chat templates to process our inputs first. Then, you can pass it to the pipeline. These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and 1B with 2 trillion tokens. Here are the key components:

• Nemotron-Cascade-2-30B-A3B↗

  NVIDIA

  We're excited to introduce Nemotron-Cascade-2-30B-A3B, an open 30B MoE model with 3B activated parameters that delivers strong reasoning and agentic capabilities. It is post-trained from the Nemotron-3-Nano-30B-A3B-Base. Nemotron-Cascade-2-30B-A3B achieves ***gold medal*** performance in both the 2025 International Mathematical Olympiad (IMO) and the International Olympiad in Informatics (IOI). It operates in both **thinking** and **instruct** (non-thinking) modes. Benchmark Nemotron-3-Nano-30B-A3B Nemotron-3-Super-120B-A12B Qwen3.5-35B-A3B Nemotron-Cascade-2-30B-A3B Requires vLLM version >= 0.17.1. The following will create API endpoints at `http://localhost:8000/v1`:

• prompt-task-and-complexity-classifier↗

  NVIDIA

  This is a multi-headed model which classifies English text prompts across task types and complexity dimensions. Tasks are classified across 11 common categories. Complexity is evaluated across 6 dimensions and ensembled to create an overall complexity score. Further information on the taxonomies can be found below. **Task types:** * Open QA: A question where the response is based on general knowledge * Closed QA: A question where the response is based on text/data provided with the prompt * Summarization * Text Generation * Code Generation * Chatbot * Classification * Rewrite * Brainstorming * Extraction * Other **Complexity dimensions:** * Overall Complexity Score: The weighted sum of the complexity dimensions. Calculated as 0.35\*CreativityScore + 0.25\*ReasoningScore + 0.15\*ConstraintScore + 0.15\*DomainKnowledgeScore + 0.05\*ContextualKnowledgeScore + 0.05\*NumberOfFewShots * Creativity: The level of creativity needed to respond to a prompt. Score range of 0-1, with a higher score indicating more creativity. * Reasoning: The extent of logical or cognitive effort required to respond to a prompt. Score range of 0-1, with a higher score indicating more reasoning * Contextual Knowledge: The background information necessary to respond to a prompt. Score range of 0-1, with a higher score indicating more contextual knowledge required outside of prompt. * Domain Knowledge: The amount of specialized knowledge or expertise within a specific subject area needed to respond to a prompt. Score range of 0-1, with a higher score indicating more domain knowledge is required. * Constraints: The number of constraints or conditions provided with the prompt. Score range of 0-1, with a higher score indicating more constraints in the prompt. * Number of Few Shots: The number of examples provided with the prompt. Score range of 0-n, with a higher score indicating more examples provided in the prompt.

• Qwen3.8-27B-Heretic-Uncensored-Q4_K_M-GGUF↗

  mlasli

  GGUF quantization of mlasli/Qwen3.8-27B-Heretic-Uncensored-BF16 (v2.1.0). Full methodology, benchmarks, and the 3-way eval are documented there. v2.1.0 fixes v2.0.0's false "uncensored" claim: the sweep now optimizes a **3-way direct / deflect / refuse judge** (not a keyword refusal count) and the BF16 checkpoint scores **92% direct / 3% refuse / 5% deflect** on the held-out harmful set (thinking OFF), with **1%** benign over-refusal. Set `enable_thinking: false` in the chat template (or the equivalent flag in your client). Ollama users can `ollama create` from the GGUF directly.

• magistral-small-2506-mlx-bf16↗

  lmstudio-community

  *👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** mistral-ai **Original model**: magistral-small **MLX quantization:** provided by LM Studio team using mlx_lm LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

• Wan2.1-T2V-14B-gguf↗

  city96

  This is a direct GGUF conversion of Wan-AI/Wan2.1-T2V-14B All quants are created from the FP32 base file, though I only uploaded FP16 due to it exceeding the 50GB max file limit and gguf-split loading not currently being supported in ComfyUI-GGUF. The model files can be used with the ComfyUI-GGUF custom node.

• gemma-3-27b-it-bnb-4bit↗

  unsloth

  Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens and 1B with 2 trillion tokens. Here are the key components: The combination of these diverse data sources is crucial for training a powerful multimodal model that can handle a wide variety of different tasks and data formats.

• HunyuanVideo_comfy↗

  Kijai

  To be used with ComfyUI native HunyuanVideo implementation, or my wrapper: https://github.com/kijai/ComfyUI-HunyuanVideoWrapper GGUF's created using city96's scripts, and only works with their nodes: https://github.com/city96/ComfyUI-GGUF

• controlnet-sd21↗

  thibaud

  Here's the first version of controlnet for stablediffusion 2.1 Trained on a subset of laion/laion-art You can use it with annotator depth/le_res but it works better with ZoeDepth Annotator. My PR is not accepted yet but you can use my fork. My fork: https://github.com/thibaudart/sd-webui-controlnet The PR: https://github.com/Mikubill/sd-webui-controlnet/pull/655#issuecomment-1481724024 The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.

• Huihui-Qwen3-VL-8B-Instruct-abliterated↗

  huihui-ai

  This is an uncensored version of Qwen/Qwen3-VL-8B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). The abliterated model will no longer say "I can’t describe or analyze this image." **Please update to the latest version of Ollama-v0.12.7.** You can use huihui_ai/qwen3-vl-abliterated:8b-instruct directly,