xClean Tools

AI Models — Daily Top 5

UPDATED 2026-09-06 01:03 PDT

2026-07-25 · SATURDAY · 11:23 PDT

  1. 1 unsloth/Laguna-S-2.1-GGUF 57,536 DOWNLOADS · 174 LIKES Unsloth published GGUF builds of poolside's Laguna S 2.1 using its Dynamic 2.0 imatrix quantization. The repo is aimed at running the model locally through llama.cpp or Unsloth Studio, with UD-Q4_K_XL among the offered quants.
  2. 2 baseten/GLM-5.2-Vision-NVFP4 494 DOWNLOADS · 92 LIKES Baseten gave GLM-5.2 sight by attaching the MoonViT vision encoder from Kimi-K2.6 through a trained PatchMerger projector. Both the text backbone and the vision tower stay frozen and byte-identical to their upstream releases, so only the projector is new. This checkpoint is quantized to NVFP4 for SGLang serving.
  3. 3 google/gemma-4-31B-it 12,511,030 DOWNLOADS · 3,363 LIKES Google DeepMind's instruction-tuned Gemma 4 at 31B parameters takes text and image input and ships under Apache 2.0. The Gemma 4 line carries a context window of up to 256K tokens and keeps the family's multilingual coverage. At over 12 million downloads it is the most pulled model on today's list.
  4. 4 Qwen/Qwen3.6-35B-A3B 6,413,105 DOWNLOADS · 2,506 LIKES Qwen shipped the first open-weight variant of Qwen3.6, a 35B mixture-of-experts model with 3B active parameters that accepts image and text input. It follows the Qwen3.5 series released in February and is distributed in Hugging Face Transformers format, with vLLM, SGLang and KTransformers listed as compatible runtimes.
  5. 5 nvidia/nemotron-3.5-asr-streaming-0.6b 840,691 DOWNLOADS · 938 LIKES Nvidia released a 0.6B streaming speech recognition model in the Nemotron 3.5 line, built around cache-aware decoding for low-latency transcription. It is the multilingual extension of the earlier English-only nemotron-speech-streaming-en-0.6b.

2026-07-24 · FRIDAY · 15:44 PDT

  1. 1 poolside/Laguna-S-2.1-NVFP4 89,186 DOWNLOADS · 129 LIKES Laguna S 2.1 is poolside's 117.6B-parameter mixture-of-experts model, with about 8.5B parameters active per token, built for agentic coding and long-horizon tasks; this is its NVFP4-quantized release for efficient inference. It is available via OpenRouter and the Vercel AI Gateway. The release has 129 likes on Hugging Face.
  2. 2 fdtn-ai/antares-1b 4,266 DOWNLOADS · 144 LIKES Antares-1b is a compact 1-billion-parameter text-generation model from fdtn-ai. Despite modest downloads, it is trending on Hugging Face with 144 likes, pointing to community interest in a small new base model. Public documentation is minimal at release.
  3. 3 Kwaipilot/KAT-Coder-V2.5-Dev 396 DOWNLOADS · 117 LIKES KAT-Coder-V2.5-Dev is a post-trained coding model from Kwaipilot, released as Hugging Face Transformers weights and compatible with vLLM and SGLang for serving. It targets software-development tasks. The early release has 117 likes on Hugging Face.
  4. 4 openbmb/MiniCPM-RobotTrack 349 DOWNLOADS · 122 LIKES MiniCPM-RobotTrack is a compact vision-language-action model from OpenBMB, built on MiniCPM4-0.5B for embodied target tracking - following a specified object as a robot moves. It extends the small MiniCPM family toward robotics. The release has 122 likes on Hugging Face.
  5. 5 nvidia/Cosmos3-Edge 30,303 DOWNLOADS · 110 LIKES Cosmos3-Edge is part of Nvidia's Cosmos 3 family of omnimodal world models for physical AI, packaged for edge deployment. World models like these aim to let robots and autonomous systems predict physical dynamics. It has 110 likes on Hugging Face.

2026-07-23 · THURSDAY · 23:34 PDT

  1. 1 microsoft/Mage-Flow 411 DOWNLOADS · 193 LIKES Mage-Flow is Microsoft's compact 4B-parameter generative stack for text-to-image generation and instruction-based image editing, released alongside a companion paper. Rather than scaling to tens of billions of parameters, it targets efficient synthesis at native resolution. The Hugging Face release drew 193 likes.
  2. 2 openbmb/MiniCPM-RobotManip 408 DOWNLOADS · 165 LIKES MiniCPM-RobotManip is a 1.5B vision-language-action model from OpenBMB built for on-device robotic manipulation. It ships as a single generalist policy meant to drive a robot from perception and instructions rather than task-specific models. The release gathered 165 likes on Hugging Face.
  3. 3 poolside/Laguna-S-2.1-GGUF 25,360 DOWNLOADS · 116 LIKES Poolside published GGUF builds of its Laguna S 2.1 model for local inference with llama.cpp, bundled with a DFlash speculative-decoding draft model for faster generation. The quantized release makes poolside's coding-oriented model runnable on consumer hardware. It has 116 likes on Hugging Face.
  4. 4 bottlecapai/ThinkingCap-Qwen3.6-27B 25,231 DOWNLOADS · 530 LIKES ThinkingCap is a finetune of Qwen3.6-27B that reaches similar capability while using about 50% fewer reasoning tokens on average, and over 90% fewer in the best cases. It targets the cost of long chain-of-thought by trimming how much the model thinks before answering. The release drew 530 likes on Hugging Face.
  5. 5 moonshotai/Kimi-K2.7-Code 766,522 DOWNLOADS · 1,255 LIKES Kimi K2.7 Code is Moonshot AI's coding-focused agentic model, built on Kimi K2.6 with gains on real-world, long-horizon software tasks. It emphasizes end-to-end completion of complex engineering workflows while improving token efficiency. With over 766,000 downloads and 1,255 likes, it was the day's most-adopted release.

2026-07-22 · WEDNESDAY

  1. 1 poolside/Laguna-S-2.1 3,056 DOWNLOADS · 411 LIKES Poolside's Laguna S 2.1 is a code-focused generation model released with a blog post and hosted access on OpenRouter and Vercel's AI Gateway. It is the most-trending new model on the Hub this cycle.
  2. 2 upstage/Solar-Open2-250B 0 DOWNLOADS · 337 LIKES Upstage released Solar Open 2, a 250B-parameter (A15B active) open model - a sizable open-weights entry from a Korean lab, drawing strong early likes on the Hub.
  3. 3 Nanbeige/Nanbeige4.2-3B 0 DOWNLOADS · 245 LIKES Nanbeige4.2-3B is a compact 3B agentic model built for tool use and multi-step tasks, part of the trend of small models tuned specifically to drive agents.
  4. 4 conradlocke/krea2-identity-edit 0 DOWNLOADS · 500 LIKES Krea 2 Identity Edit is a community image model for identity-preserving edits - changing a scene while keeping a face consistent. It is trending on likes despite being freshly posted.
  5. 5 Motif-Technologies/Motif-3-Beta 125 DOWNLOADS · 162 LIKES Motif-3-Beta is a preview checkpoint of Motif Technologies' next model, shared ahead of the final release for early testing - an increasingly common way labs gather community feedback on the Hub.

2026-07-21 · TUESDAY

  1. 1 prism-ml/Ternary-Bonsai-27B-gguf 432,196 DOWNLOADS · 889 LIKES Prism ML's ternary-weight Bonsai 27B in GGUF form: full 27B-class reasoning at a fraction of the memory, per the whitepaper. The most-downloaded build of the family this week (an MLX 1-bit variant also trends).
  2. 2 baidu/Unlimited-OCR 2,237,351 DOWNLOADS · 2,580 LIKES Baidu's OCR model pitched as one-shot long-horizon parsing: whole documents in a single pass instead of page-by-page pipelines. 2.2M downloads with day-one ms-swift community integration.
  3. 3 DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 62,842 DOWNLOADS · 221 LIKES A community Qwen3.6-27B finetune whose model card claims arc-c scores above 700 in 8-bit. Benchmark numbers on community cards are self-reported - read them as claims, not results.
  4. 4 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF 2,133,420 DOWNLOADS · 2,383 LIKES GGUF quantizations of Empero's Qwythos-9B with a 1M-token context window. Over 2.1M downloads puts it among the Hub's most-pulled models this week.
  5. 5 HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 1,997,690 DOWNLOADS · 2,960 LIKES An uncensored community build of Qwen3.6-35B-A3B nearing 2M downloads. Sustained demand for unrestricted local models remains one of the Hub's clearest usage signals.

2026-07-17 · FRIDAY

  1. 1 zai-org/GLM-5.2 534,698 DOWNLOADS · 4,078 LIKES Zhipu's flagship open model line updated to 5.2, one of the most-liked releases on the Hub this cycle, shipping with a technical report and an active community.
  2. 2 thinkingmachines/Inkling 7,870 DOWNLOADS · 973 LIKES Thinking Machines' image-text-to-text model, published in BF16 and NVFP4 builds with Tinker Cookbook integration and full documentation.
  3. 3 prism-ml/Bonsai-27B-gguf 1,045,182 DOWNLOADS · 403 LIKES A 1-bit 27B model in GGUF form promising full 27B-class reasoning at a fraction of the memory, per Prism ML's whitepaper. Past a million downloads.
  4. 4 OpenMOSS-Team/MOSS-Transcribe-Diarize 83,160 DOWNLOADS · 250 LIKES An end-to-end 0.9B audio model that transcribes and diarizes in a single pass - who spoke and what they said, without a pipeline of separate tools.
  5. 5 ATH-MaaS/OvisOCR2 10,795 DOWNLOADS · 153 LIKES An OCR-focused vision model released with a technical report and online demo. Document-to-structured-text is the workhorse task behind most RAG pipelines.