サイト内検索

AI モデル 84759

• gemini-2.5-flash-preview-09-2025↗

  Google

• lang-id-voxlingua107-ecapa-gguf↗

  handy-computer

  Ported from upstream commit 0253049, pinned 2026-10-05. Validated against the SpeechBrain reference at transcribe.cpp commit aa4d0f47 on 2026-10-08. Spoken language identification over 107 languages: SpeechBrain's ECAPA-TDNN trained on VoxLingua107. NOT a transcription model: a run returns the model's language labels ranked by probability, optionally restricted to a caller-chosen set. Takes 16 kHz mono WAV; scores up to the first 30 s of a clip. Top-1 accuracy on FLEURS multilingual (3,000 utterances), scored on cpu. Measured at transcribe.cpp `cf62265a` on 2026-10-08.

• MuLaCover↗

  HeartMuLa

• Huihui-Qwen3-VL-32B-Instruct-abliterated↗

  huihui-ai

• Huihui-Xing4.0-29B-A4B-abliterated↗

  huihui-ai

• granite-4.1-8b-GGUF↗

  ibm-granite

  > [!NOTE] > This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite `.safetensors` model. > > Please reference the base model's full model card here: > https://huggingface.co/ibm-granite/granite-4.1-8b

• Meta-Llama-3-70B-Instruct-GGUF↗

  jburmeister

• jina-embedding-t-en-v1↗

  jinaai

• jina-embeddings-v5-text-nano-mlx↗

  jinaai

• SuperQwen3.8-27b-abliterated-GGUF↗

  Jiunsong

  **A one-DGX-Spark Q4_K_M release with a native MTP draft, Q8_0 vision projector, bounded reasoning, and a verified 262K context path.** This is the llama.cpp build of `Jiunsong/SuperQwen3.8-27b-abliterated`: the corrected rank-4 OBLITERATUS model, not an adapter and not the earlier incorrect lineage. The target, MTP draft, and multimodal projector are separate so text-only users do not pay for the projector, while vision and native speculative decoding remain available. The target contains 433 Q4_K, 65 Q6_K, and 353 F32 tensors. The MTP draft contains 10 Q4_0 and 8 F32 tensors. The projector deliberately retains unsupported or sensitive matrices: 83 Q8_0, 27 F16, and 224 F32 tensors.