voxcpm2 needs about 3.7 GB of memory at Q8_0 (a 2.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.0 GB to 5.0 GB (F16).
VoxCPM2: 2B‑parameter multilingual text‑to‑speech model
VoxCPM2 is a tokenizer‑free, diffusion autoregressive TTS model with 2.38B parameters. It supports 30 languages and outputs 48 kHz mono PCM. The model is licensed under Apache‑2.0 and can be used for commercial projects.
Good at
- Multilingual TTS without language tags
- Voice design from natural‑language description
- Real‑time streaming on high‑end GPUs
Limits
- No vision support
- Requires 8 k context for memory estimates
- No explicit language list beyond 30 languages
Best for
- Creating multilingual synthetic voices
- Voice cloning from short clips
- Real‑time TTS applications
Who it’s for. Developers building multilingual TTS services or voice‑clone applications. The model is open‑source and free for commercial use under Apache‑2.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K | 1.7 GB | 2.4 GB | Fits | Get file → | |
| Q8_0 | 2.8 GB | 3.7 GB | Fits | Get file → | |
| Q8_0 | 3.0 GB | 3.9 GB | Fits | Get file → | |
| F16 | 5.0 GB | 6.1 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K (1.69 GB, ~2.4 GB memory). For 16 GB VRAM use Q8_0 (2.83 GB, ~3.7 GB memory). For 24 GB VRAM use F16 (4.97 GB, ~6.1 GB memory). Estimates are approximate.
What GPU do you need for voxcpm2?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 3.9 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.0 GB file, about 6.1 GB in use).
Which voxcpm2 quant should you choose?
Q8_0 (2.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about voxcpm2
How much VRAM does voxcpm2 need?
About 3.7 GB at Q8_0 with an 8K context window. That is the 2.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run voxcpm2 on an 8 GB GPU?
Yes, with F16: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of voxcpm2 GGUF?
It depends on the quant: file is 0.0 GB, Q4_K is 1.7 GB, Q8_0 is 2.8 GB, Q8_0 is 3.0 GB, F16 is 5.0 GB.
Where can I download voxcpm2 GGUF?
The files are on Hugging Face in the cstr/voxcpm2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does voxcpm2 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run VoxCPM2 on 8 GB VRAM?
Yes, the Q4_K quantized file is 1.69 GB and requires about 2.4 GB memory at 8 k context.
Does VoxCPM2 support voice cloning?
Yes, it supports zero‑shot voice cloning from a short reference audio clip.