サイト内検索
AI モデル 2119
- Veena↗
maya-research
Veena is a state-of-the-art neural text-to-speech (TTS) model developed by Maya Research, designed for English and Indian languages. Built on a Llama architecture backbone, Veena generates natural, expressive speech with emotional tone, remarkable quality, and ultra-low latency. It represents the foundation of our voice intelligence work, bringing human-like voice to the two most spoken languages in the world. **Veena** is a 3B parameter autoregressive transformer model based on the Llama architecture. It is designed to synthesize high-quality speech from text in Hindi and English, including code-mixed scenarios. The model outputs audio at a 24kHz sampling rate using the SNAC neural codec. To use Veena, you need to install the `transformers`, `torch`, `torchaudio`, `snac`, and `bitsandbytes` libraries.
- flux-3-image-klein-prompt-upsampler-abliterated-GGUF↗
prithivMLmods
- Zarafusionex-1.1-L2-7B-GGUF↗
TheBloke
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible. The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license. As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
- opendecider-small-GGUF↗
manjunathshiva
GGUF builds of OpenDecider-small, the 4B OpenDecider decision model, for **LM Studio**, **Ollama** and anything else built on llama.cpp. Best for decisions it has never seen: the best general accuracy and calibration of the 4B models (zero-shot on typed-decisions). A decision model answers typed questions (`choice`, `score`, yes/no) about any text or JSON with a probability for every option, instead of generating text. The opendecider package builds the exact prompt the model was trained on and reads the option probabilities from the server's token log-probabilities. On typed-decisions (2,000 questions), the Q8_0 build gives the same top answer as the full-precision model on 1,975 (98.8%), at the same accuracy: Measured through Ollama's llama.cpp engine; LM Studio runs the same engine and returned identical log-probabilities on the same file. **Q8_0 is the recommended file**; Q4_K_M is for machines with little memory.
- samantha-dolphin-llama-3-GGUF↗
mradermacher
- Pony-Diffusion-V6-XL-GGUF↗
morikomorizz
The default FP16 model can take up 6-7gb just to load vram and do image Diffusion, with a separate gguf, the unet model only needs 2.8gb vram on KSampler / Processing Image. Base Model: https://civitai.com/models/257749/pony-diffusion-v6-xl All credits to the original creator: https://civitai.com/user/PurpleSmartAI Support My Work & Request Custom Quantization: It takes time, testing, and electricity to compress these models perfectly
- Gemma-4-E4B-Samantha-GGUF↗
mradermacher
- Samantha-120b-i1-GGUF↗
mradermacher
- wav2vec2-xlsr-mongolian↗
sammy786
- Qwen3.8-Flash-Next-REAP-288-GGUF↗
sh0wie
This is the REAP-288 build in GGUF, for llama.cpp and the tools built on it (Ollama, LM Studio, and similar). It is the 180B-class MoE with its experts pruned 512 -> 288 per layer, converted directly from the bf16 source in a single quantization step, so each file loses accuracy exactly once rather than stacking a re-quantization on top of an existing 4-bit build. The pruned model scores 91.5% on HumanEval (149 of 164), against 93.9% for the unpruned full model. That number is measured on the MLX 4-bit lineage; the GGUF quants share the same kept-expert selection and derive from the same bf16 source. If you run MLX on Apple Silicon instead of llama.cpp, use the 4-bit MLX build. The pmlx engine and its speedups apply to the MLX builds, not to GGUF; nothing on this card depends on it.