xClean Tools

AI Models — Daily Top 5

UPDATED 2026-09-06 01:03 PDT

2026-08-23 · SUNDAY · 13:02 PDT

  1. 1 EschaLabs/Qwen3.8-27B-Escha-W2 1,892 DOWNLOADS · 120 LIKES Escha Labs published a 2-bit quantized build of Qwen3.8-27B that keeps the full 27B parameter count in 10.15 GB of weights. The card says the model, its KV cache, and a 64k context fit on a single 24 GB consumer card, or 128k context with a tuned config. It has drawn 1,892 downloads and 120 likes.
  2. 2 Audio8/Audio8-TTS-Preview-0.1b 1,093 DOWNLOADS · 115 LIKES Audio8 released a 0.1B-parameter preview text-to-speech model that handles speech generation and zero-shot voice cloning. The card bills it as the smallest zero-shot TTS worth running and links audio samples alongside a companion GitHub repository. It has 1,093 downloads and 115 likes.
  3. 3 incoai/Qwen3.8-27B-DFlash2-GGUF 39,691 DOWNLOADS · 116 LIKES GGUF conversions of incoai's DFlash 2 draft model for Qwen3.8-27B. It is not a standalone language model: it runs inside a speculative decoding server and drafts tokens for the target model to verify. At 39,691 downloads it is by far the most pulled model on today's list.
  4. 4 sensenova/SenseNova-U1.5-8B-MoT 1,445 DOWNLOADS · 112 LIKES SenseNova's latest native unified multimodal checkpoint, built on NEO-unify and aimed at image generation and editing. The card credits strengthened patchify layers, better data quality and distribution, revised task formulation, prompt enhancement, and a reworked post-training pipeline, listing six user-visible improvements. It has 1,445 downloads and 112 likes.

2026-08-22 · SATURDAY · 13:04 PDT

  1. 1 deepseek-ai/DeepSeek-V4-Flash-0731 2,976,281 DOWNLOADS · 3,626 LIKES DeepSeek published the official release of V4-Flash, superseding the preview with what the card calls substantially enhanced agentic capabilities. It keeps the same structure as the DSpark variant, including an attached speculative decoding module, and the team reports it outperforming DeepSeek-V4-Pro (Preview) on the benchmarks listed. Close to 3 million downloads and 3,626 likes.
  2. 2 LBH-123-AI/Minimax_h3_latent_Upscaler 0 DOWNLOADS · 156 LIKES This is a neural upscaler that operates directly on Minimax H3's 24-channel video latents, raising spatial resolution while leaving the time dimension untouched. The intended workflow is to generate video cheaply at low resolution, upscale the latent in place, then refine at the target size. It has 156 likes and no recorded downloads yet.
  3. 3 ornith-ai/Ornith-1.5-9B-GGUF 174,817 DOWNLOADS · 158 LIKES Ornith-1.5 is a 9B model built around end-to-end self-improvement, extending Ornith-1.0, which was developed on top of Qwen3.5 and Gemma4 with extra continued pretraining and post-training. The new version widens the loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction and solution rollouts. The GGUF build has about 175,000 downloads.
  4. 4 empero-ai/Qwen3.8-9B-Distill-GGUF 126,213 DOWNLOADS · 135 LIKES Empero released GGUF quantizations of its Qwen3.8-9B, a full-parameter distillation of the 2.4T-parameter Qwen3.8 A95B into the Qwen3.5-9B architecture. The files target llama.cpp, Ollama, LM Studio, Jan and KoboldCpp, and the card is deliberately limited to choosing a quant and running it. Downloads stand near 126,000.
  5. 5 DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 2,894,845 DOWNLOADS · 2,203 LIKES This community fine-tune of Qwen3.6-27B ships both regular and MTP Neo MAX imatrix GGUF quants, plus a range of other quant types. The author claims it is the first fine-tune to exceed 700 on ARC-C at both 8-bit and 4-bit. With nearly 2.9 million downloads and 2,203 likes, it is the most downloaded community fine-tune among today's trending models.

2026-08-21 · FRIDAY · 13:08 PDT

  1. 1 superwhisper/s1-mini 1,136 DOWNLOADS · 180 LIKES Superwhisper published S1-mini, a Qwen3-based text-generation model whose card points it at speech recognition work and, specifically, text normalization and inverse text normalization - the step that turns spoken words in a transcript into their written forms. The repository ships Transformers-format safetensors weights.
  2. 2 DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF 155,208 DOWNLOADS · 159 LIKES DavidAU released GGUF builds of a Cold Fusion fine-tune of Qwen3.8-27B, trained with a GAIN and Unsloth recipe the card says holds 99 percent of BF16 performance at both 8-bit and 4-bit. The card also claims the model spends between half and a tenth as many thinking tokens as the base while keeping its reasoning, and clears the 27B Qwen core benchmarks.
  3. 3 peculiar-ragdoll/Qwen-Sharp-Chat-Templates 0 DOWNLOADS · 172 LIKES Qwen Sharp Chat Templates is not a model but a set of drop-in chat templates for Qwen 3.5, 3.6 and 3.8, tagged for llama.cpp and MLX. The author says the Sharp template tunes those models for knowledge work and coding, and that Qwen3.8-27B at medium effort answers with fewer thinking tokens while getting more capable.
  4. 4 ornith-ai/Ornith-1.5-9B 10,304 DOWNLOADS · 148 LIKES ornith-ai released Ornith-1.5-9B, which its card presents as a step toward building foundation models through end-to-end self-improvement. It extends Ornith-1.0, itself continued-pretrained and post-trained on top of Qwen3.5 and Gemma4, by widening the loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction and rollouts.
  5. 5 incoai/Qwen3.8-27B-DFlash2 37,056 DOWNLOADS · 141 LIKES incoai published Qwen3.8-27B-DFlash2, a draft model for Qwen3.8-27B rather than a standalone language model. It runs inside a speculative decoding server, proposing tokens for the larger target model to verify, and is built on a block-diffusion approach with tags for SGLang.

2026-08-20 · THURSDAY · 13:07 PDT

  1. 1 OBLITERATUS/Qwen3.8-27B-OBLITERATED 4,415 DOWNLOADS · 223 LIKES OBLITERATUS published an abliterated build of Alibaba's Qwen3.8-27B, claiming zero refusals across a set of 842 harmful prompts. The card describes six rounds of surgery on the weights using residue mining and multi-direction SVD, on the argument that refusal behavior is encoded as directions in activation space across dozens of layers rather than sitting in a system prompt. It has 223 likes on about 4,400 downloads.
  2. 2 ornith-ai/Ornith-1.5-35B-A3B 1,713 DOWNLOADS · 203 LIKES Ornith-1.5-35B-A3B is a mixture-of-experts model with 35 billion total parameters and roughly 3 billion active per token, presented as a step toward building foundation models through end-to-end self-improvement. It extends Ornith-1.0, which was developed on top of Qwen3.5 and Gemma4 with continued pretraining, mid-training and post-training. A GGUF conversion of the same weights has passed 53,000 downloads.
  3. 3 orcarouter/Qwen3.8-27B-Uncensored-GGUF 52,382 DOWNLOADS · 232 LIKES orcarouter's uncensored GGUF build of Qwen3.8-27B is the most liked model on today's list, with 232 likes and more than 52,000 downloads. It is tagged for llama.cpp and for abliteration, and is labeled image-text-to-text, carrying the base model's vision input. The same team's MLX and FP8 conversions trended earlier this week.
  4. 4 huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF 187,008 DOWNLOADS · 195 LIKES Huihui's GGUF release is an abliterated build of Qwen3.8-27B and the most downloaded model on today's list at more than 187,000 pulls. The card calls the method a crude proof of concept for removing refusals without TransformerLens, notes that the first 15 layers were retained without ablation, and flags multi-token prediction and the vision path as untouched.
  5. 5 z-lab/Qwen3.8-27B-DFlash2 12,235 DOWNLOADS · 149 LIKES DFlash 2 is a draft model for Qwen3.8-27B rather than a standalone language model: it runs inside a speculative decoding server and proposes tokens for the larger model to verify. It uses a block-diffusion drafting approach and is packaged for SGLang. The repo mirrors incoai/Qwen3.8-27B-DFlash2 and has about 12,200 downloads.

2026-08-19 · WEDNESDAY · 13:05 PDT

  1. 1 JonathanColetti/Qwen3.8-27B-Uncensored-GGUF 766,812 DOWNLOADS · 463 LIKES GGUF quantizations of an uncensored Qwen3.8-27B lead the day's model list with about 767,000 downloads. The build keeps the multi-token-prediction head that abliteration normally strips, re-saving the model through transformers and verifying the mtp tensors are present. The publisher says refusal behaviour is substantially reduced, not eliminated.
  2. 2 huihui-ai/Huihui-Qwen3.8-27B-abliterated 7,207 DOWNLOADS · 164 LIKES huihui-ai published an abliterated Qwen3.8-27B that removes refusal directions without using TransformerLens. The first 15 layers are left unablated, and both the MTP head and the vision tower are unmodified. Its GGUF conversion trends alongside the weights, drawing more than 94,000 downloads of its own.
  3. 3 empero-ai/Qwen3.8-9B-Distill 4,354 DOWNLOADS · 139 LIKES Empero released Qwen3.8-9B, a full-parameter distillation of the 2.4T-parameter Qwen3.8 A95B model into the Qwen3.5-9B architecture. The student was trained on roughly 70,000 curated teacher traces from the team's internal set. Weights ship in Hugging Face Transformers format and run on vLLM and SGLang.
  4. 4 AEON-7/Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16 7,805 DOWNLOADS · 138 LIKES AEON-7 posted a BF16 abliteration of Qwen3.8-27B, labelled an early-access draft rather than a finished release. The vision tower and native MTP head are left as the unmodified base, and the publisher says the ablation targets coherence rather than a minimal KL divergence. A later NVFP4 version is planned from this full-precision master.
  5. 5 AtomicChat/Qwen3.8-27B-GGUF 121,717 DOWNLOADS · 124 LIKES Atomic Chat built its own GGUF quantizations of Qwen3.8-27B from Qwen's original weights using an in-house importance matrix, and has drawn about 122,000 downloads. The calibration corpora behind the builds are public and the repo publishes per-quantization measurements. The model runs in the Atomic Chat client with thinking toggles.

2026-08-18 · TUESDAY · 13:07 PDT

  1. 1 orcarouter/Qwen3.8-27B-Uncensored-MLX 0 DOWNLOADS · 209 LIKES An MLX build of an abliterated Qwen3.8-27B, packaged for Apple silicon and tagged by its publisher for red-teaming work. The multimodal checkpoint has drawn 209 likes and reports no downloads yet, one of several uncensored derivatives of Qwen's 27-billion-parameter model trending on the Hub today.
  2. 2 HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF 27,745 DOWNLOADS · 186 LIKES HauhauCS ships an aggressive uncensored variant of Qwen3.8-27B as GGUF with its FastMTP speculative decoding, claiming up to 3.02 times the document generation throughput of a non-MTP build and 35.2 percent more than standard embedded MTP. The publisher reports zero refusals across its own 465-prompt test.
  3. 3 Blackfrost-AI/Qwen3.8-27B-ABLITERATED-GGUF 134,149 DOWNLOADS · 147 LIKES Blackfrost published a full standard K-quant ladder, Q2_K through Q8_0, of its abliterated Qwen3.8-27B, with both vision projectors included and no importance-matrix quants. The dense multimodal build targets llama.cpp and has passed 134,000 downloads, the second highest among today's candidates.
  4. 4 fal/MiniMax-H3-Realism-People-LoRA 20,600 DOWNLOADS · 255 LIKES fal published a LoRA adapter for the MiniMax H3 video model tuned for realistic people, covering close-up faces, skin texture, expressions and documentary-style camera movement. The card documents 19 before-and-after pairs generated at the same prompt and seed with the adapter on and off. Its 255 likes lead every model on today's list.
  5. 5 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF 150,262 DOWNLOADS · 137 LIKES This GGUF is a double-refined abliteration of Qwen3.8-27B, built on an existing ARA abliteration and given two further full-weight passes aimed at residual refusals. The publisher reports refusals dropping from 3 in 100 prompts to 0 or 1 while keeping behavioral damage low, at a KL of about 0.0085. It leads today's candidates with over 150,000 downloads.

2026-08-17 · MONDAY · 13:06 PDT

  1. 1 orcarouter/Qwen3.8-27B-Uncensored-FP8 15,812 DOWNLOADS · 424 LIKES An FP8 build of an abliterated Qwen3.8-27B, the multimodal checkpoint behind most of this week's top open-weight uploads. Refusal behavior is stripped rather than retrained, and the repo tags it for red-teaming use. It leads a cluster of uncensored repackagings of the same base model published in FP8, GGUF and BF16 formats.
  2. 2 HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive 332,718 DOWNLOADS · 688 LIKES An uncensored multimodal build of the previous-generation Qwen3.6-27B, shipped as GGUF and reporting zero refusals across the publisher's 465-prompt test. The author steers most users to the Balanced sibling instead, citing the same refusal rate with more stable sampling for agentic coding and reasoning work. It carries 688 likes and roughly 333,000 downloads.
  3. 3 CohereLabs/North-Micro-Vision-Instruct 19,213 DOWNLOADS · 112 LIKES Cohere released North Micro Vision Instruct, a 2.4-billion-parameter open-weight vision-language model with native-resolution image support, under Apache 2.0. It is positioned as a compact base for prototyping, task-specific fine-tuning and specialized multimodal applications rather than as a frontier system.
  4. 4 empero-ai/Qwen3.8-27B-Ridge-GGUF 9,222 DOWNLOADS · 110 LIKES A mixed-precision GGUF of the official Qwen3.8-27B checkpoint at about 3.7 bits per weight. Rather than applying a uniform quant ladder, the mix is probed for the model's architecture of 64 layers alternating Gated-DeltaNet and gated attention blocks. It targets llama.cpp, Ollama, LM Studio, jan and KoboldCpp.
  5. 5 empero-ai/Qwen3.8-9B 540 DOWNLOADS · 106 LIKES A full-parameter distillation of Qwen3.8 2.4T A95B into the 9-billion-parameter Qwen3.5 architecture, trained on roughly 70,000 curated teacher traces. The weights ship in Hugging Face Transformers format and run on vLLM, SGLang and other runtimes that already support Qwen3.5.