xClean Tools

AI Models — Daily Top 5

UPDATED 2026-09-06 01:03 PDT

2026-08-30 · SUNDAY · 13:02 PDT

  1. 1 Comfy-Org/MiniMax-H3 21,374,217 DOWNLOADS · 1,616 LIKES Comfy-Org's repackaging of MiniMax-H3 leads Hugging Face activity today with more than 21 million downloads and 1,616 likes. The repository ships the diffusion model as ComfyUI-ready single files, along with an NVFP4 Qwen3-VL-32B text encoder that the maintainers say runs without a Blackwell GPU. They recommend the int8_convrot build over fp8_scaled for users on PyTorch with CUDA 13.
  2. 2 ornith-ai/Ornith-1.5-35B-A3B-GGUF 2,087,570 DOWNLOADS · 349 LIKES ornith-ai published GGUF builds of Ornith-1.5-35B-A3B, a 35B-parameter model whose name indicates roughly 3B active parameters per token. The team describes Ornith-1.5 as extending Ornith-1.0, itself continued-pretrained from Qwen3.5 and Gemma4, by widening an end-to-end self-improvement loop beyond scaffold and rollout. The quantized repository has passed 2 million downloads.
  3. 3 orcarouter/GLM-5.3-Flash-Uncensored-FP8 684 DOWNLOADS · 101 LIKES An FP8 build of GLM-5.3-Flash with refusal behavior stripped out drew 101 likes on Hugging Face despite fewer than 700 downloads. Its tags mark it as abliterated and image-text-to-text, pointing to a vision-capable variant of the GLM-5.3 Flash tier served in 8-bit floating point. The repository ships no documentation.

2026-08-29 · SATURDAY · 13:04 PDT

  1. 1 FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree 0 DOWNLOADS · 140 LIKES FastVideo published the recommended checkpoint of its FastH3 preview, which generates synchronized video and audio from a text prompt in four transformer forward passes. The step-1300 model was trained with data-free DMD2 distillation and VSA-H3 at 90 percent sparsity. It leads today's trending models with 140 likes.
  2. 2 logic65/Qwen3.8-Whittle-MoE-27B-A17.8B 19,714 DOWNLOADS · 101 LIKES This research preview whittles Qwen3.5 down to a 27B mixture-of-experts model with 17.8B active parameters. Version 2.2.1, dated today, fixes a reasoning abort in which the model could end its turn inside its own chain of thought. The maintainer traced it to a stop gate trained on chat-template thinking blocks that the training data never closed.
  3. 3 ibm-granite/granite-4.2-30b 2,946 DOWNLOADS · 90 LIKES IBM released Granite 4.2 30B, a text generation model the company tags for reasoning, extended thinking and tool calling. It ships as part of the Granite 4.2 language model collection, with a technical blog and a public GitHub repository alongside the weights. The checkpoint has drawn 2,946 downloads and 90 likes.
  4. 4 orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF 20,275 DOWNLOADS · 97 LIKES An abliterated build of Qwen3.8 Flash Next, packaged in GGUF for local inference. The repository is tagged as a mixture-of-experts model with an image-text-to-text pipeline, and carries no README text. It is the most downloaded entry in today's trending set, with 20,275 downloads against 97 likes.

2026-08-28 · FRIDAY · 13:05 PDT

  1. 1 zai-org/GLM-5.3 0 DOWNLOADS · 1,051 LIKES GLM-5.3 keeps the same base model as GLM-5.2 and takes all of its gains from post-training, targeting complex coding and long-horizon tasks. Z.ai reports a 50 percent improvement over GLM-5.2 on its in-house code benchmark and open-source state of the art on Terminal Bench 3.0 and Agents' Last Exam. The card also flags emergent cyber capability as post-training scaled.
  2. 2 tencent/Hy4-preview 0 DOWNLOADS · 224 LIKES A preview release of Tencent's Hunyuan 4 mixture-of-experts model, published under Apache 2.0 with bilingual Chinese and English documentation. It is tagged for text generation and conversational use and is mirrored on ModelScope and cnb.cool alongside the Hugging Face repository.
  3. 3 pipecat-ai/phonellm-alpha-1 64 DOWNLOADS · 107 LIKES PhoneLLM Alpha 1 is a voice-agent model fine-tuned from NVIDIA Nemotron 3 Nano 30B-A3B for phone calls. It is a hybrid Mamba-Transformer mixture of experts with 30 billion total and 3.5 billion active parameters, trained by full-parameter supervised fine-tuning in NVIDIA NeMo, and it carries a 262,144-token context in bfloat16.
  4. 4 peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF 16,011 DOWNLOADS · 93 LIKES A dynamic imatrix requantization of Ornith-1.5-35B-A3B packaged as GGUF for llama.cpp and aimed at agentic coding. The publisher reports that at 4-bit and 22 GB it fixes real codebase issues at the rate of a far larger hosted model and holds up in multi-turn conversation, while being poor at trivia. It is the most downloaded model on the board.
  5. 5 tencent/WeMM-Embedding-9B 385 DOWNLOADS · 91 LIKES A universal multimodal embedding model built on Qwen3.5 that maps text, images and video into one representation space. Tencent publishes it with a technical report and a GitHub repository, tagged for feature extraction and sentence-transformers use.

2026-08-27 · THURSDAY · 13:05 PDT

  1. 1 unsloth/Qwen3.8-Flash-Next-GGUF 4,354 DOWNLOADS · 441 LIKES Unsloth published GGUF builds of Qwen3.8-Flash-Next made with its Dynamic 3.0 quantization, which the team says reaches better accuracy than other leading quants. Running them currently calls for Unsloth's llama.cpp pull request or its desktop app, where the model exposes thinking controls. The repo has about 4,354 downloads and 441 likes.
  2. 2 BreezeBlue/Breeze-TTS-2 240 DOWNLOADS · 123 LIKES BreezeBlue open-sourced the Breeze TTS 2 weights on August 25 together with PyTorch inference code on GitHub. The model covers speech generation, voice cloning and voice design. Its source code is Apache 2.0, but the weights, derivative models and self-hosted outputs are limited to research and non-commercial use.
  3. 3 moonshotai/Kimi-K3 2,829,554 DOWNLOADS · 11,035 LIKES Moonshot AI released Kimi K3, a 2.8-trillion-parameter open-weight multimodal agentic model the lab calls its most capable to date. It is built on Kimi Delta Attention and Attention Residuals, with native vision and a one-million-token context window, and is presented as the first open model of the 3T class. It has roughly 2.8 million downloads and 11,035 likes.
  4. 4 alibaba-pai/MiniMax-H3-Acc-LoRAs 609 DOWNLOADS · 108 LIKES Alibaba's PAI team published acceleration LoRAs for MiniMax-H3, applying Parallel Decoding Distillation so the video model generates in only a few inference steps. The release includes 8-step variants for the model's first-last-frame-to-video mode and is used through the VideoX-Fun repository. It has about 609 downloads and 108 likes.
  5. 5 apodex/Apodex-1.1-mini 1,306 DOWNLOADS · 88 LIKES Apodex released Apodex-1.1-mini, a reasoning-first model aimed at long-horizon research work that goes past search and report writing to act on files, data, code and tools. The card says it runs on AgentOS with an asynchronous agent team, holding task state, adapting its plan and coordinating parallel work. It has about 1,306 downloads and 88 likes.

2026-08-26 · WEDNESDAY · 13:05 PDT

  1. 1 Qwen/Qwen3.8-Flash-Next 2,551 DOWNLOADS · 3,522 LIKES Qwen published Qwen3.8-Flash-Next as post-trained weights in Hugging Face Transformers format, tagged for image-text-to-text use. The repo says the artifacts run under Transformers, vLLM, SGLang and TokenSpeed, and points users who want managed inference to the hosted Qwen API instead. It has drawn about 3,500 likes and 2,551 downloads.
  2. 2 zai-org/GLM-5.3-Flash 0 DOWNLOADS · 705 LIKES Z.ai released GLM-5.3-Flash, which it calls the first natively multimodal model in the GLM-5 series. It carries 320 billion total parameters with 18 billion active, and the team says it beats GLM-5.2 across benchmarks and real workloads at a tenth of the price while approaching Claude Opus 4.8 on coding and agentic tests. The repo has about 705 likes.
  3. 3 thomsonreuters/Thomson-1.0-Small 214 DOWNLOADS · 109 LIKES Thomson Reuters released Thomson-1.0-Small, a foundation model it describes as proficient across specialized and general-purpose domains, alongside a technical report on continual learning of frontier models for sovereign AI. The weights ship in Hugging Face Transformers format, and the repo config identifies a Qwen3.5 mixture-of-experts architecture. It has about 109 likes and 214 downloads.

2026-08-25 · TUESDAY · 13:05 PDT

  1. 1 alibaba-pai/MiniMax-H3-Fun-Controlnet-Union 2,194 DOWNLOADS · 117 LIKES Alibaba PAI published a ControlNet-Union checkpoint for the MiniMax-H3 video generator, trained with the VideoX-Fun pipeline. The single checkpoint conditions generation on Canny, Depth, HED, MLSD or Pose control videos and also performs video inpainting. It has about 2,200 downloads and 117 likes on Hugging Face.
  2. 2 outsourc-e/Qwen3.8-27B-Unleashed-GGUF 35,044 DOWNLOADS · 111 LIKES An abliterated build of Qwen3.8 27B is published as GGUF quantizations in nine tiers, using imatrix dynamic quants for local inference. The uploader says two low-bit tiers, UD-IQ1_M and UD-IQ2_S, briefly shipped broken and were withdrawn, then rebuilt and load-tested, so copies pulled before August 21 should be replaced.

2026-08-24 · MONDAY · 13:04 PDT

  1. 1 orcarouter/Qwen3.8-27B-Uncensored 10,482 DOWNLOADS · 162 LIKES Qwen3.8-27B-Uncensored is a community-modified build of Qwen3.8 27B, published as safetensors for transformers and tagged for image-text-to-text use. The repository carries the abliterated tag, marking a variant altered to remove the base model's refusal behavior. It is the day's only new model to trend on Hugging Face, with about 10,500 downloads and 162 likes.