kokoro 82m needs about 0.7 GB of memory at Q8_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.1 GB (Q8_0) to 0.2 GB (F16).
82 M‑parameter open‑weight TTS model
Kokoro 82M is an open‑weight TTS model with 82 million parameters. It uses the StyleTTS2 architecture and supports 178‑symbol IPA vocab across multiple languages. The model is Apache‑2.0 licensed and available in GGUF format.
Good at
- Fast inference on modest hardware
- Low disk footprint
- Consistent multilingual TTS
Limits
- No vision support
- Limited to 8 k context
- Requires 8 k context for memory estimates
Best for
- Personal TTS projects
- Low‑cost audio generation
- Rapid prototyping of voice packs
Who it’s for. Developers and hobbyists looking for a lightweight, open‑source TTS model. The Apache‑2.0 license allows deployment in production or personal projects without restrictions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → |
For 8 GB VRAM use Q8_0 (0.14 GB file, 0.7 GB memory at 8 k context). For slightly larger memory budgets use F16 (0.16 GB file, 0.7 GB memory). Both quants give similar quality with Q8_0 saving disk space.
What GPU do you need for kokoro 82m?
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 (0.2 GB file, about 0.7 GB in use).
Which kokoro 82m quant should you choose?
Q8_0 (0.1 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kokoro 82m
How much VRAM does kokoro 82m need?
About 0.7 GB at Q8_0 with an 8K context window. That is the 0.1 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 kokoro 82m on an 8 GB GPU?
Yes, with F16: the 0.2 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kokoro 82m GGUF?
It depends on the quant: Q8_0 is 0.1 GB, F16 is 0.2 GB.
Where can I download kokoro 82m GGUF?
The files are on Hugging Face in the cstr/kokoro-82m-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 kokoro 82m 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 Kokoro 82M on 8 GB VRAM?
Yes, the Q8_0 quant uses about 0.7 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does Kokoro support voice packs?
Yes, voice packs are available in a sister repo and can be used with the same GGUF model.
Is there a license restriction for commercial use?
The model is Apache‑2.0 licensed, allowing commercial deployment without additional fees.