OmniVoice GGUF GGUF weights for omnivoice.cpp, a C++17/GGML port of OmniVoice (k2 fsa/OmniVoice). Multilingual zero shot TTS, 646 languages, 24 kHz mono. Runs on CPU, CUDA, ROCm, Metal, Vulkan. Files Two GGUFs load together : omnivoice base {variant}.gguf Qwen3 0.6B backbone, text tokens omnivoice tokenizer {variant}.gguf HuBERT + DAC + RVQ, tokens 24 kHz audio variant base tokenizer use case F32 2.46 GB 734 MB reference, debug, conversion BF16 1.23 GB 373 MB source faithful, max precision Q8 0 656 MB 289 MB recommended default Q4 K M 407 MB 252 MB lowest VRAM Quick start Backends Set GGML BACKEND to force a device, otherwise the runtime picks the best one available. value target CUDA0 NVIDIA GPU, fastest path on Ada / Blackwell Vulkan0 Cross vendor GPU (AMD / Intel / NVIDIA) Metal Apple Silicon GPU CPU CPU fallback, x86 variant auto selected Quantization policy Tokenizer GGUFs are not uniform quants. Three categories get a dedicated treatment : tensor dtype across all variants RVQ codebooks, fc, fc2, project in / project out F32 Snake activation alpha F32 Conv kernels with non alignable rows (K=7,3,1) F16 (in Q variants) Same fallback as llama.cpp tensor type fallback : F16 has no…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy