サイト内検索

AI モデル 2119

• ZeroTTS↗

  zeroweight-ai

  **The most accurate open Vietnamese TTS we know of — 4× fewer word errors than the next best model**, and it runs faster than real time on a laptop CPU. Every system reads **raw text** — dates, numbers and acronyms verbatim, exactly as they appear in the wild, with no text frontend in front of the model. **4× fewer word errors than the next-best system**, and the fastest of the four on CPU. The gap is much wider in latency than in throughput: the two XTTS fine-tunes also beat real time (0.71×) but need seconds to emit their first sample, while OmniVoice is 6× *slower* than real time. All three are sized and tuned for a GPU, and it shows.

• Gemma2-9b-Neuro-sama-Q4_K_M-GGUF↗

  neifuisan

• Cosmos-Transfer1-7B-Sample-AV-Single2MultiView↗

  NVIDIA

• drama3-expressive-medium-GGUF↗

  pentacoxian-dev

  **Built From Fish Audio.** This is a fine-tuned and quantized derivative of Fish Audio Drama 3. Fish Audio does not sponsor or endorse it. Drama 3 follows an acting direction at the start of a line, but it mostly ignores one placed in the middle: `[calm] It's fine, really. [voice breaking] I just miss her.` tends to stay calm, or to go silent at the second direction. drama3-expressive-medium was fine-tuned to change delivery where the direction says. It also speaks the whole line and ends cleanly far more often. It keeps all 256 experts and runs in 24 GB of VRAM. No reference audio: each sample's seed makes up its own voice, speaking the line's language (`--task tts` with no `voice_ref`). The first table keeps the words fixed and changes only the opening direction; the second changes the delivery mid-line.

• GLM-5.2-NVFP4↗

  NVIDIA

  The NVIDIA GLM-5.2 NVFP4 model is the quantized version of ZAI’s GLM-5.2 model, which is an auto-regressive language model that uses an optimized transformer architecture. GLM-5.2 is a Mixture-of-Experts (MoE) model for reasoning and coding that uses sparse attention (with an IndexShare indexer) to support a long context. For more information, please check here. The NVIDIA GLM-5.2 NVFP4 model is quantized with Model Optimizer. **GOVERNING TERMS:** Use of the model is governed by the MIT License, same as the base model. Developers looking to take off-the-shelf, pre-quantized models for deployment in AI Agent systems, chatbots, RAG systems, and other AI-powered applications.

• rtdetr_v2_r18vd↗

  PekingU

  The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian Zhao, Qinyao Chang, Kui Huang, Guanzhong Wang, Yi Liu. RT-DETRv2 refines RT-DETR by introducing selective multi-scale feature extraction, a discrete sampling operator for broader deployment compatibility, and improved training strategies like dynamic data augmentation and scale-adaptive hyperparameters. These changes enhance flexibility and practicality while maintaining real-time performance. This model was contributed by @jadechoghari with the help of @cyrilvallez and @qubvel-hf RT-DETRv2 consistently outperforms its predecessor across all model sizes while maintaining the same real-time speeds.

• gemma-3n-E2B-it-unsloth-bnb-4bit↗

  unsloth

  Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal input, handling text, image, video, and audio input, and generating text outputs, with open weights for pre-trained and instruction-tuned variants. These models were trained with data in over 140 spoken languages. Gemma 3n models use selective parameter activation technology to reduce resource requirements. This technique allows the models to operate at an effective size of 2B and 4B parameters, which is lower than the total number of parameters they contain. For more information on Gemma 3n's efficient parameter management technology, see the Gemma 3n page. With instruction-tuned models, you need to use chat templates to process our inputs first. Then, you can pass it to the pipeline.

• Llama-3-Kimodo-GGML↗

  LocalAI-io

  Native GGML/GGUF text encoder used by Kimodo. This is the reusable LLM2Vec encoder only; download a matching Kimodo diffusion model separately, for example `Kimodo-SMPLX-RP-v1-GGML`. From a kimodo.cpp checkout with the Hugging Face CLI installed, install both with: The downloader installs the recommended Q8_0 variant by default. Select a different one with `--text-quantization bf16|q8_0|q6_k|q5_k|q4_k|q4_k_m`. Every variant is one monolithic weight GGUF and uses the same `tokenizer.gguf`. Kimodo reads individual tensor ranges from the monolith, so streaming one layer at a time does not require separate per-layer files.

• Krea2-Turbo-Distill-4step-LoRA↗

  lvladikov

  > 🆕 **New: a 3-step LoRA** takes Krea 2 Turbo from 8 steps down to 3, at three quarters of this LoRA's denoising time, with more fine detail (fine texture 1.15× the 8-step teacher's on its 22 test prompts). This 4-step LoRA stays the closest to Turbo's own 8-step pictures. **Half the steps · ~1.6× faster end to end · 45% of the gap to the 8-step teacher closed · texture at 1.03× the teacher's, verified clean · teacher preferred on only 6 of 45 judged renders · 12 trained resolutions · 78,000 training samples · 21 days on one RTX 3090.** A LoRA for **Krea 2 Turbo** that reduces the minimum usable step count from **8 to 4** — Turbo's own model and sigmas, half the denoising passes, and the fine texture that 4-step Turbo loses put back.

• NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Uncensored-GGUF↗

  AtomicChat

  NVIDIA's refusal behaviour projected out of the released weights, baked into Atomic Dynamic GGUF builds and measured against the original. On held-out JailbreakBench prompts refusals fall from 97.5% to 0%, and with thinking on from 30 of 30 to none (2 of 30 on the 22 and 29 GB files). MMLU stays where it was: 81.35% before, 81.75% after (2000 questions, McNemar p = 0.29). Tool calls and long context are unaffected. You can now run the Uncensored Nemotron 3.5 Bolt in Atomic Chat , locally on your own machine. Made from the full-precision release, not from NVIDIA's 24 GB file, and measured on one stand against the other public Bolt abliterations: at 22 GB ours is the closest to the original and the only one that neither refuses with thinking off nor breaks into repeated text ( table ). The refusal is written into the residual stream by every kind of block: the edit covers the Mamba-2 outputs, the attention outputs, the shared experts and the latent projection through which all routed experts write. Same Atomic Dynamic layouts and importance matrix as our Nemotron 3.5 Bolt quants ; each file is the size of the original build with the same name. *28 Oct 2026: re-split from 2 GB shards: `AD-IQ2_XS` and `AD-IQ1_M_S` are now a single file each, `AD-Q4_K_M` two files cut at 45 GB. The weights are unchanged (tensor-for-tensor identical).*