전체 검색
AI 모델 84759
- ganesh-mini-1.0↗
Executespec
- mms-tts-dga↗
facebook
- POCKET-26B-GGUF↗
FINAL-Bench
> ### ⭐ Latest and flagship models > [](https://huggingface.co/FINAL-Bench/VKORE-46M-NPU) [](https://huggingface.co/FINAL-Bench/Darwin-27B-ZTC-v5) > [](https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6) [](https://huggingface.co/collections/FINAL-Bench/darwin-family-699987b1f652864af0122193) [](https://huggingface.co/FINAL-Bench) [](https://vidraft.net) [](https://thevc.kr/vidraft) > ### 🆕 **POCKET-Qwen3.8-Flash-Next** — a **180B** model running on a **laptop with 8 GB VRAM + 32 GB RAM** · **4.17 tok/s measured**. > [](https://huggingface.co/FINAL-Bench/POCKET-Qwen3.8-Flash-Next-GGUF) []() []() []() > ### 🆕 **POCKET-Zimage-CPU** — photoreal **images** in **46 s** on a **CPU only**. No GPU, no CUDA, no Python. > [](https://huggingface.co/FINAL-Bench/POCKET-Zimage-CPU) [](https://huggingface.co/spaces/FINAL-Bench/POCKET-Zimage-CPU) []()
- isl-latn-10mb-after-ppt-Dp-100mb-packed-bfdiso-ckpt500_seed455↗
francesca9805
- wav2vec2-large-xlsr-gu↗
gchhablani
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Gujarati using the OpenSLR SLR78 dataset. When using this model, make sure that your speech input is sampled at 16kHz. The model can be used directly (without a language model) as follows, assuming you have a dataset with Gujarati `sentence` and `path` fields: 90% of the OpenSLR Gujarati Male+Female dataset was used for training, after removing few examples that contained Roman characters. The colab notebook used for training can be found here.
- roberta2roberta_L-24_cnn_daily_mail↗
Google
- t5-efficient-large-nh4↗
Google
- t5gemma-s-s-prefixlm↗
Google
- videoprism-lvt-base-f16r288↗
Google
- stsb-roberta-base-off-topic↗
govtech