bark-small needs about 1.0 GB of memory at Q8_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.2 GB (Q4_K) to 0.8 GB (F16).
Bark Small – 404M parameter text-to-speech model in GGUF format
Bark Small is a 404 billion‑parameter text‑to‑speech model converted to GGUF for native C++ inference. It uses a 3‑stage hierarchical transformer and an EnCodec decoder to produce 24 kHz mono PCM audio. The model supports 13 languages with pre‑trained speaker prompts.
Good at
- Text‑to‑speech generation
- Multilingual speaker support
- Low‑latency inference
Limits
- Requires at least 0.8 GB VRAM for Q4_K at 8k context
- No vision or image generation capabilities
- MIT license – free for commercial use
Best for
- Embedded TTS in edge devices
- Rapid prototyping of voice assistants
- Generating synthetic audio for datasets
Who it’s for. Developers building lightweight TTS systems who need a small, open‑source model. Ideal for projects that require low VRAM usage and fast inference on commodity hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.8 GB | 1.4 GB | Fits | Get file → |
For 8 GB VRAM use the Q4_K variant (0.24 GB file, 0.8 GB memory at 8k context). If more VRAM is available, Q8_0 (0.44 GB file, 1 GB memory) offers higher precision. The F16 variant (0.81 GB file, 1.4 GB memory) provides the best quality but needs more memory.
What GPU do you need for bark-small?
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 F16 (0.8 GB file, about 1.4 GB in use).
Which bark-small quant should you choose?
Q8_0 (0.4 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 Q4_K at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about bark-small
How much VRAM does bark-small need?
About 1.0 GB at Q8_0 with an 8K context window. That is the 0.4 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 bark-small on an 8 GB GPU?
Yes, with F16: the 0.8 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bark-small GGUF?
It depends on the quant: Q4_K is 0.2 GB, Q8_0 is 0.4 GB, F16 is 0.8 GB.
Where can I download bark-small GGUF?
The files are on Hugging Face in the cstr/bark-small-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 bark-small use?
Hugging Face lists the license as mit. 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 Bark Small on 8 GB VRAM?
Yes, the Q4_K quantization requires only 0.8 GB memory at 8k context, well within an 8 GB VRAM budget.
Does Bark Small support image generation?
No, Bark Small is a text‑to‑speech model and does not support vision or image generation.