xClean Tools

AI Models — Daily Top 5

UPDATED 2026-11-02 01:15 PST

2026-08-07 · FRIDAY · 13:06 PDT

  1. 1 LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF 332,992 DOWNLOADS · 423 LIKES A community finetune of Qwen3.6-35B-A3B, shipped in GGUF form for local inference, has pulled 332,992 downloads and 423 likes. The uploader describes it as an uncensored mixture-of-experts build with vision support. Its download count is far ahead of every other new entry on Hugging Face's trending list today.
  2. 2 lightx2v/Minimax-h3-Turbo 0 DOWNLOADS · 110 LIKES LightX2V published a distilled Turbo LoRA for MiniMax-H3, covering text-to-video, image-to-video and reference-to-video, with a GitHub repo for reproducing the results. Community ComfyUI ports already run it at four sampling steps. It has drawn 110 likes and a set of third-party conversions.
  3. 3 Kijai/MiniMax-H3-TAE 0 DOWNLOADS · 88 LIKES Kijai trained a small 2D autoencoder for MiniMax-H3 so ComfyUI can show usable previews while a video generates. The author calls the result imperfect but better than latent2rgb, and now points users to a properly trained tiny video autoencoder from another developer. It runs through a preview-override node in ComfyUI-KJNodes.
  4. 4 nvidia/Alpamayo2-Super 1,591 DOWNLOADS · 88 LIKES NVIDIA released Alpamayo 2 Super, a 34B-parameter foundation model for autonomous-vehicle development that pairs a 32B vision-language backbone with a 2B diffusion expert. It is built to cover several AV development tasks in one model and forms part of the company's wider Alpamayo open platform.

2026-08-06 · THURSDAY · 13:07 PDT

  1. 1 larryvrh/MiniMax-H3-Turbo-Lora 0 DOWNLOADS · 267 LIKES A community LoRA for the MiniMax-H3 video model that renders joint video plus synchronized stereo audio in 4 sampling steps instead of the usual roughly 20, about a 5x sampling speedup. The final checkpoint of this training round is sharp but carries known artifacts, and third-party ComfyUI conversions are already circulating.
  2. 2 LiquidAI/LFM2.5-2.6B-GGUF 12,790 DOWNLOADS · 123 LIKES LiquidAI's official GGUF build of LFM2.5-2.6B, part of a new family of hybrid models designed for on-device deployment. LFM2.5 extends the LFM2 architecture with additional pre-training and reinforcement learning, and the GGUF packaging targets local inference with llama.cpp. The repo counts 12,790 downloads and 123 likes.
  3. 3 Abiray/Minimax-H3-nvfp4-INT4-INT8-Convrot 272,963 DOWNLOADS · 106 LIKES A community-compiled collection of quantized and pruned MiniMax-H3 (Hailuo 3.0) weights in INT4, INT8, mixed, and NVFP4 formats for local inference environments such as ComfyUI. By unifying the formats in one structured repository it targets consumer GPUs with 16 to 24 GB of VRAM, and it has logged 272,963 downloads.
  4. 4 sakamakismile/Qwen3-VL-32B-Heretic-MiniMax-H3-NVFP4 0 DOWNLOADS · 106 LIKES An NVFP4 mixed-precision re-quantization of the Heretic uncensored Qwen3-VL-32B text encoder used with MiniMax-H3 video generation. At 15.7 GB the build fits on a single 16 GB card, continuing the push to squeeze the full H3 pipeline onto consumer hardware.
  5. 5 openai/whisper-large-v3 5,337,172 DOWNLOADS · 6,107 LIKES OpenAI's Whisper large-v3 is a state-of-the-art model for automatic speech recognition and speech translation, trained on more than 5 million hours of labeled data. Years after release it still ranks among the most-downloaded models on Hugging Face, with about 5.3 million downloads and over 6,100 likes.

2026-08-05 · WEDNESDAY · 13:07 PDT

  1. 1 ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot 0 DOWNLOADS · 274 LIKES ComfyUI conditioning encoders and generation tails built from an uncensored Heretic variant of Qwen3-VL-32B, shipped as BF16 and INT8 ConvRot builds. The package repurposes the vision-language model as H3 text and vision encoders for local generation workflows, and tops today's Hugging Face trending list at 274 likes.
  2. 2 deepgrove/maple-preview 0 DOWNLOADS · 136 LIKES DeepGrove's Maple-Preview is an open-source 20B-A1B ternary-weight reasoning model packed into a 5.31 GB checkpoint with 131K context. The team reports state-of-the-art reasoning for its weight class, IMO-level problem solving, and over 200 tokens per second on a Mac mini M4, five to sixteen times faster than efficient models like Gemma 4 and gpt-oss.
  3. 3 mistralai/Shieldstral-1.0-3B 166 DOWNLOADS · 121 LIKES Mistral's Shieldstral 1.0 is a compact 3B-parameter, policy-adaptive multimodal safety classifier. Rather than predicting fixed moderation categories, it scores text and image content against a safety policy written in natural language, letting guardrails be retargeted to new policies at inference time without retraining.
  4. 4 LGAI-EXAONE/K-EXAONE-2.0-750B-A37B 325 DOWNLOADS · 129 LIKES LG AI Research released K-EXAONE 2.0, a frontier-scale multilingual mixture-of-experts model with 750B total and 37B active parameters. Scaled to more than three times its predecessor through upcycling, continual pretraining, and difficulty-focused mid-training, it is described as broadly competitive with leading open-weight models.
  5. 5 black-forest-labs/FLUX.1-dev 546,530 DOWNLOADS · 13,996 LIKES Black Forest Labs' FLUX.1-dev remains on Hugging Face's trending list long after release, with roughly 547,000 recent downloads and nearly 14,000 likes. The open-weight text-to-image model stays one of the most widely used bases for image generation and fine-tuning across the ecosystem.

2026-08-04 · TUESDAY · 13:04 PDT

  1. 1 LiquidAI/LFM2.5-2.6B 47,393 DOWNLOADS · 108 LIKES LFM2.5-2.6B is part of Liquid AI's LFM2.5 family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with a 128K context window and agentic post-training, and the card claims tool use and instruction following competitive with models four times larger. The repo has passed 47,000 downloads.
  2. 2 realrebelai/MiniMax-H3_GGUFs 40,010 DOWNLOADS · 97 LIKES A community GGUF packaging of MiniMax's H3 video generation model for ComfyUI, and the most downloaded of the H3 quant repos this week. It ships FL2VA and REF2V unet variants plus a quantized Qwen3-VL text encoder, pointing users to the official audio and video VAEs. Downloads have passed 40,000.
  3. 3 nvidia/NVIDIA-NemotronLabs-VoiceChat-11B 80 DOWNLOADS · 77 LIKES NVIDIA NemotronLabs VoiceChat 11B is a speech model focused on natural conversational behavior. The card demonstrates smooth turn-taking with roughly 450 ms responses, barge-in handling where the model yields instantly when interrupted, and live tool calling, with code published in the NVIDIA NeMo Speech repository.
  4. 4 huihui-ai/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF 14,046 DOWNLOADS · 76 LIKES An uncensored build of DeepSeek-V4-Flash-0731 produced with abliteration to strip refusal behavior, distributed as GGUF files for llama.cpp. The maintainer describes it as a crude proof-of-concept for removing refusals without TransformerLens. It has drawn over 14,000 downloads.
  5. 5 KRAFTON/A.X-K2-Raon-Speech-21B-A3B 2,137 DOWNLOADS · 78 LIKES A.X K2 Raon-Speech is a bilingual English and Korean speech language model with about 21.2B total and 3.5B active parameters. Built on SK Telecom's A.X K2 Light mixture-of-experts text backbone, it adds KRAFTON's independently trained AuT speech encoder and a Mimi-style neural audio codec to unify speech understanding and generation in one model.