Starstruk Logo MarkStarstruk

runtime-llamacpp-v0.1.2

tursodatabase/tursoruntime-llamacpp-v0.1.2Jun 21, 2026by LauraGPT

AI Summary

A runtime update for FunASR llama.cpp that introduces support for q8 GGUF models, offering a significant reduction in model size without compromising accuracy.

Key Highlights

  • Support for q8 GGUF models (~half the size of f16 with same accuracy).
  • SenseVoice, Paraformer, and Fun-ASR-Nano support.
  • Built-in FSMN-VAD for voice activity detection.
  • No Python or build required; prebuilt binaries available.

New Features

  • Support for q8 GGUF models
  • SenseVoice and Paraformer ASR capabilities

Full Release Notes

Prebuilt self-contained binaries for running **SenseVoice** (and Paraformer / Fun-ASR-Nano) locally with the FunASR llama.cpp / GGUF runtime — built-in FSMN-VAD, whisper.cpp-style on-device ASR, strong on Chinese & Cantonese.

**New:** q8 GGUF models are ~half the size of f16 with the same accuracy.

```bash
bash download-funasr-model.sh sensevoice ./gguf
llama-funasr-sensevoice -m ./gguf/sensevoice-small-q8.gguf --vad ./gguf/fsmn-vad.gguf -a audio.wav
```

No Python, no build. Linux (x64/arm64), macOS (arm64), Windows (x64). Docs: `runtime/llama.cpp/README.md`.