xClean Tools

AI Models — Daily Top 5

UPDATED 2026-09-06 01:03 PDT

2026-08-16 · SUNDAY · 13:03 PDT

  1. 1 unsloth/Qwen3.8-27B-NVFP4 276,269 DOWNLOADS · 196 LIKES Unsloth published an NVFP4 quantization of Qwen3.8-27B built with its Dynamic V3.0 preview recipe, keeping multi-token prediction for faster inference and adding developer-role support for agentic tools such as Codex. The repo has drawn roughly 276,000 downloads and 196 likes. Qwen3.8-27B redistributions in NVFP4, FP8 and GGUF dominate the day's trending list.
  2. 2 Comfy-Org/MiniMax-Music-3 0 DOWNLOADS · 145 LIKES Comfy-Org repackaged MiniMax Music 3 for ComfyUI, shipping the diffusion transformer weights in fp16, fp32 and int8 along with full and pruned text encoders. The files drop straight into a local ComfyUI install, and the repository has collected 145 likes since MiniMax released the original model.
  3. 3 froggeric/Qwen-Fixed-Chat-Templates 0 DOWNLOADS · 1,161 LIKES This repository ships a single drop-in Jinja chat template that replaces the official ones for Qwen 3.5, 3.6 and 3.8, fixing rendering errors, KV cache invalidation, wasted tokens and stalls during agentic runs. It targets LM Studio, llama.cpp, vLLM and MLX, and has gathered more than 1,100 likes.
  4. 4 TenStrip/10Eros-Max 0 DOWNLOADS · 186 LIKES 10Eros-Max is an experimental video generation model that folds patterns learned from LTX 2.3, Wan 2.2 and the Krea 2 image model into a MiniMax H3 base. It uses a unified 52-block transformer with modality-specific projectors for video, audio and conditioning inputs, and supports both text-to-video and image-to-video.
  5. 5 IndexTeam/IndexTTS-2.5 3,422 DOWNLOADS · 115 LIKES IndexTTS-2.5 is a zero-shot text-to-speech model that clones a voice from a single reference clip, now covering Chinese, English, Japanese, Spanish and Arabic. The update adds speaking speed control, faster inference and better handling of Pinyin, CMU phonemes and Kana, with emotion control kept separate from timbre.

2026-08-15 · SATURDAY · 13:05 PDT

  1. 1 Qwen/Qwen3.8-27B-FP8 123,157 DOWNLOADS · 412 LIKES Qwen published FP8 weights for its post-trained Qwen3.8-27B image-text model, quantized at fine granularity with a block size of 128. The repository ships in Hugging Face Transformers format and is listed as compatible with vLLM, SGLang and similar serving stacks, and third-party NVFP4 and abliterated repacks of the same base model are already circulating.
  2. 2 Gazingstars123/Anima-2.9B 16,829 DOWNLOADS · 186 LIKES Anima-2.9B is a text-to-image model for anime and illustration that is still in training, distributed as a single diffusion file. It is supported in ComfyUI and Forge-Neo, and the author has released a standalone LoRA trainer alongside an sd-scripts fork. The next stage is pretraining on 10M general samples to improve prompt understanding.
  3. 3 dots-studio/dots3-note-prev 240 DOWNLOADS · 159 LIKES dots-studio released a preview of dots3-note, a multimodal model that handles audio alongside text and images. The card documents evaluations on general reasoning, agent tasks and multimodal understanding, with a full technical report still to come, and lists deployment paths through Transformers and SGLang.
  4. 4 Cactus-Compute/needle2 4,497 DOWNLOADS · 117 LIKES Needle 2 is a 45M-parameter open model for tool calling, device use and structured extraction that ships as a single 14MB binary and runs a full session in 28MB of RAM. Cactus Compute compressed it to roughly 2 bits with its own quantizer and engine, and reports it trading wins with small models 5x to 70x larger.
  5. 5 Motif-Technologies/Motif-3 1,861 DOWNLOADS · 111 LIKES Motif 3 is a decoder-only mixture-of-experts language model with 314B total parameters and 13.2B activated per token, built in-house by Motif Technologies. Its architecture centers on Grouped Differential Latent Attention, which combines grouped differential attention with the compressed key-value representation used in multi-head latent attention.

2026-08-14 · FRIDAY · 13:05 PDT

  1. 1 Qwen/Qwen3.8-27B 2 DOWNLOADS · 8,708 LIKES Qwen published Qwen3.8-27B, a post-trained image-text-to-text model released under Apache 2.0 in Hugging Face Transformers format. The weights are compatible with Transformers, vLLM and SGLang, and community FP8, NVFP4 and GGUF builds appeared alongside the launch. It leads the day's list with 8,708 likes.
  2. 2 meta-models/Muse-Glimmer-30B-GGUF 228,364 DOWNLOADS · 267 LIKES Meta Superintelligence Lab's Muse Glimmer 30B is now available in GGUF form for llama.cpp, bundling two quantized text builds, a perception encoder for image input and a drafter model for speculative decoding. The Apache 2.0 release drew 228,364 downloads, the most of any model in the day's list.
  3. 3 Qwen/Qwen3.8-2.4T-A95B-FP8 9,334 DOWNLOADS · 180 LIKES Qwen also released an FP8 build of Qwen3.8-2.4T-A95B, a mixture-of-experts text model with 2.4 trillion total parameters and 95 billion active per token, served in Qwen Studio as qwen3.8-max. Quantization is fine-grained FP8 with a block size of 128, targeting vLLM and SGLang deployments.
  4. 4 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 34,137 DOWNLOADS · 139 LIKES NVIDIA released Nemotron 3.5 Lightning in BF16, a 30-billion-parameter model with 3 billion parameters active per token, trained on the company's own pre-training and post-training datasets. It covers six languages and ships under the OpenMDW 1.1 license, with 34,137 downloads so far.
  5. 5 LiquidAI/LFM2.5-VL-3B 1,794 DOWNLOADS · 131 LIKES Liquid AI's LFM2.5-VL-3B is a multimodal model built for on-device deployment, pairing an LFM2.5-2.6B language backbone with a SigLIP2 NaFlex vision encoder. Over its LFM2-VL predecessor it adds improved grounding, object detection from natural language queries and full-page OCR.

2026-08-13 · THURSDAY · 13:05 PDT

  1. 1 unsloth/Muse-Glimmer-30B-GGUF 352,023 DOWNLOADS · 387 LIKES Unsloth has published GGUF quantizations of Muse Glimmer 30B, an image-text-to-text model credited to Meta Superintelligence Lab and dated August 2026. The repository documents builds down to 2-bit and a toggle for thinking mode, and has passed 350,000 downloads.
  2. 2 deepseek-ai/DeepSeek-V4-Pro-0813 0 DOWNLOADS · 242 LIKES DeepSeek has released DeepSeek-V4-Pro-0813, the official version of V4-Pro that supersedes the preview. It keeps the preview model structure and attaches a DSpark speculative decoding module, and the technical report claims stronger agentic capability and benchmark gains that are most pronounced in production environments.
  3. 3 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 44,859 DOWNLOADS · 227 LIKES NVIDIA has posted an NVFP4 build of Nemotron-3.5-Lightning-30B-A3B, a mixture-of-experts model with 30 billion total and 3 billion active parameters. The card describes a hybrid Mamba-2, MoE and attention architecture with context up to 1M tokens and six supported languages.
  4. 4 MiniMaxAI/MiniMax-Music3 25 DOWNLOADS · 217 LIKES MiniMax has released Music 3, a music generation model that produces complete songs of up to five minutes from lyrics and a detailed description. It combines an 8B global language model for long-range structure with a 0.6B local model for frame-level acoustic detail and a continuous hidden-state synthesis system.
  5. 5 unsloth/MiniMax-H3-GGUF 111,222 DOWNLOADS · 148 LIKES Unsloth has published GGUF quantizations of MiniMax-H3, an omni-modal system that generates video with native stereo audio, up to 15 seconds at 24 fps with 32 kHz sound. Both halves of the runtime ship in the repository, which targets stable-diffusion.cpp and other local runners.

2026-08-11 · TUESDAY · 01:04 PDT

  1. 1 endless-frontier/BigBang-v1 617 DOWNLOADS · 157 LIKES BigBang-v1 is an open image-and-text model from endless-frontier, built on a Qwen3.5 mixture-of-experts backbone and released with transformers-ready safetensors weights. Its authors argue that progress stalls when training tasks stay inside the limits of human knowledge, and propose verifiable frontier tasks whose solutions can be checked by formal methods, computation or simulation.
  2. 2 lightx2v/MiniMax-H3-Prompt-Rewriter-LoRA 268 DOWNLOADS · 119 LIKES LightX2V has published an open LoRA adapter that rewrites prompts for text-to-audio-video generation with MiniMax-H3, so the rewriting step can run locally instead of through a hosted service. The PEFT weights target the H3 base generator and are distributed for use with the LightX2V inference stack.
  3. 3 inclusionAI/Ling-3.0-tiny 0 DOWNLOADS · 89 LIKES InclusionAI has added a small member to the Ling 3.0 line: a hybrid reasoning mixture-of-experts model with 7.9 billion total parameters and 1.3 billion activated per token. It is aimed at agentic and reasoning work at low inference cost, and ships in BF16, FP8 and INT4 weights for local and resource-constrained deployment.

2026-08-10 · MONDAY · 13:03 PDT

  1. 1 meta-models/Muse-Glimmer-30B 0 DOWNLOADS · 601 LIKES Muse Glimmer is a 30-billion-parameter Apache 2.0 model from Meta Superintelligence Lab, distilled from Muse Spark and built around a dedicated perception encoder for agentic work on consumer hardware. It combines multi-step reasoning, tool use, multimodal understanding and failure recovery in one model. The official and community GGUF builds are folded into this entry.

2026-08-09 · SUNDAY · 13:03 PDT

  1. 1 Kijai/MiniMax-H3_comfy 0 DOWNLOADS · 230 LIKES A collection of MiniMax-H3 video model weights converted for use inside ComfyUI, published with notes on pairing them with a few-step distillation LoRA and the sampler settings that behave well at low strength. The author's experimental quantised builds, including a 4-bit weight format, are folded in here. It leads today's trending models with about 230 likes.
  2. 2 drbaph/MiniMax-H3-Turbo-Lora-ComfyUI 0 DOWNLOADS · 229 LIKES Third-party ComfyUI conversions of the MiniMax-H3 Turbo LoRA, an adapter that produces joint video and synchronised audio in substantially fewer sampling steps than the standard workflow. The repository packages pruned-model compatibility variants of the original adapter rather than new weights. It trails the base conversions by a single like at about 229.
  3. 3 Akahsizrr/fuse-1-Lite 448 DOWNLOADS · 87 LIKES A mixture-of-experts model that fuses LiquidAI's LFM2.5-2.6B with Qwen3.6-35B-A3B behind expert routing, aimed at coding and Python generation. It is released under Apache 2.0 in the roughly 5B-parameter class, positioned for efficient inference rather than frontier scale. The repository reports about 448 downloads against 87 likes.