VoxCPM1.5 — GGUF weights for llama.cpp-omni
GGUF-converted weights of openbmb/VoxCPM1.5
for the C++/ggml engine llama.cpp-omni
(tools/omni/voxcpm2). Runs VoxCPM1.5 TTS + voice cloning natively on
CPU / Metal / CUDA / Vulkan — no PyTorch runtime required.
Files
| File | Format | Size | Component |
|---|---|---|---|
VoxCPM-1.5-BaseLM-F16.gguf |
F16 | ~974 MB | Base language model |
VoxCPM-1.5-BaseLM-Q8_0.gguf |
Q8_0 | ~519 MB | Base language model, 8-bit (recommended) |
VoxCPM-1.5-Acoustic-F16.gguf |
F16 | ~867 MB | Acoustic stack (ResidualLM + FSQ + CFM + AudioVAE) |
Output: 44.1 kHz mono. Use one BaseLM (Q8_0 recommended) + the Acoustic file.
Usage
./voxcpm2-cli -t "Hello from VoxCPM 1.5." -o out.wav \
VoxCPM-1.5-BaseLM-Q8_0.gguf VoxCPM-1.5-Acoustic-F16.gguf
# voice cloning: add -r speaker.wav
Verified on Apple M4 Pro / Metal (RTF ~1.68). Flags: --cfg, --timesteps,
--seed, --temperature, -r (clone), --prompt-wav/--prompt-text
(reference-transcript clone), --cpu. License/terms inherit from the upstream model.