pocket tts needs about 0.9 GB of memory at its main file (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.2 GB to 0.6 GB.
Pocket TTS – lightweight text‑to‑speech GGUF model
Pocket TTS is a ~0.0796B parameter text‑to‑speech model designed for efficient CPU inference. The GGUF conversions include a model file and an mmproj file per language, enabling direct use with llama‑cpp’s built‑in Pocket TTS support. The model runs at ~5.5–6x realtime on a desktop CPU.
Good at
- Fast CPU inference
- Low memory footprint
- Multimodal projector support
Limits
- No GPU acceleration
- Single‑language per pair
- License cc‑by‑4.0
Best for
- Local TTS on CPUs
- Embedded audio generation
- Rapid prototyping of speech synthesis
Who it’s for. Developers and hobbyists who need a small, efficient TTS model that runs locally without a GPU. The model is ideal for projects requiring quick, real‑time audio synthesis on standard desktop hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.2 GB | 0.8 GB | Fits | Get file → | |
| — | 0.2 GB | 0.8 GB | Fits | Get file → | |
| — | 0.2 GB | 0.8 GB | Fits | Get file → | |
| — | 0.2 GB | 0.8 GB | Fits | Get file → | |
| — | 0.2 GB | 0.8 GB | Fits | Get file → | |
| — | 0.6 GB | 1.2 GB | Fits | Get file → | |
| — | 0.6 GB | 1.2 GB | Fits | Get file → |
The available GGUF files are 0.16 GB and 0.61 GB. The 0.16 GB file requires approximately 0.9 GB of VRAM at 8 k context, while the 0.61 GB file requires about 1.3 GB. Both fit comfortably on systems with 8 GB of VRAM, making either file suitable for low‑budget setups.
What GPU do you need for pocket tts?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 the main file (0.6 GB file, about 1.3 GB in use).
Which pocket tts quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.2 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 pocket tts
How much VRAM does pocket tts need?
About 0.9 GB at its main file with an 8K context window. That is the 0.2 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 pocket tts on an 8 GB GPU?
Yes, with the smaller files: the 0.6 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of pocket tts GGUF?
It depends on the quant: file is 0.2 GB, file is 0.2 GB, file is 0.2 GB, file is 0.2 GB, file is 0.2 GB, file is 0.6 GB and 1 more.
What context length does pocket tts support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 4K.
Where can I download pocket tts GGUF?
The files are on Hugging Face in the EryriLabs/pocket-tts-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 pocket tts use?
Hugging Face lists the license as cc-by-4.0. 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 Pocket TTS on 8 GB VRAM?
Yes, both the 0.16 GB and 0.61 GB GGUF files fit within 8 GB of VRAM, with memory usage around 0.9 GB and 1.3 GB respectively at 8 k context.
Does Pocket TTS support vision?
Yes, the model includes a multimodal projector, enabling vision capabilities when used with llama‑cpp.
What languages are available?
Each language has its own GGUF pair; the repository includes French and Welsh, among others, each with a dedicated mmproj file.