サイト内検索
AI モデル 85004
- Qwen3-Coder-30B-A3B-Ilograph-Instruct-GGUF↗
mradermacher
- RxDecide-1.7B-GGUF↗
mradermacher
- Self-Certainty-Qwen3-8B-Base-OpenRS-i1-GGUF↗
mradermacher
- shadow-clown-7B-dare-GGUF↗
mradermacher
- Solon_Athens_v2-i1-GGUF↗
mradermacher
- spikingkiki-122b-a10b-i1-GGUF↗
mradermacher
- synoema-coder-7b-v6-0.1.0a3-GGUF↗
mradermacher
- Unhinged-Qwen2.5-R1-1M-Uncensored-BF16-i1-GGUF↗
mradermacher
- vibevoice.cpp-models↗
mudler
**Brought to you by the LocalAI team** — the creators of LocalAI, the open-source AI engine that runs any model — LLMs, vision, voice, image, video — on any hardware. No GPU required. Quantized GGUF weights for vibevoice.cpp, a C/C++ port of Microsoft VibeVoice (TTS + ASR) on top of `ggml`. `scripts/quantize_gguf.py` in the source repo selectively quantizes only the LM matmul weights — attention q/k/v/o, ffn gate/up/down, and lm_head — to Q8_0. Everything else (1-D conv kernels, RMSNorm scales, biases, layer-scale gammas, token embeddings, small scalars) passes through unchanged. The conv1d implementation in vibevoice.cpp casts kernels to F16 inline rather than dequantizing on the fly, so quantizing those would corrupt the convolution outputs.
- moss-transcribe-diarize↗
OpenASR
**Joint transcription and speaker diarization in a single 0.9B-parameter model — know who said what, and when** Native speech-to-text in the **OpenASR** runtime — engineered for peak performance on CPU & GPU, **no Python at inference time**. RTF = real-time factor on the fixed 11s JFK clip (**lower is faster**); RAM peak measured per pack in an isolated subprocess. JFK ΔWER compares each quantized build's JFK transcript to this model's fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy. **q8_0** is the recommended default — near-reference quality at a fraction of the footprint.
