Fun CosyVoice3 0.5B 2512 needs about 1.2 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.4 GB (Q2_K) to 3.4 GB (F32).
Fun CosyVoice3 0.5B 2512 – lightweight TTS model
Fun CosyVoice3 0.5B 2512 is a text‑to‑speech model based on the cosyvoice3‑2512 architecture. It contains 0.859 billion parameters and is released under Apache‑2.0. The model supports zero‑shot multilingual synthesis and can be run with cosyvoice.cpp.
Good at
- Zero‑shot multilingual TTS
- Low‑latency streaming
- Pronunciation inpainting
Limits
- No vision support
- Requires 8 k context for memory estimates
- License is Apache‑2.0
Best for
- Voice cloning demos
- Low‑latency audio generation
- Production TTS pipelines
Who it’s for. Developers and researchers needing a small, open‑source TTS model for multilingual applications. The model is suitable for local inference on modest hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q2_K_L | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_XXS | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q3_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_0 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_XXS | 0.6 GB | 1.1 GB | Fits | Get file → | |
| Q4_1 | 0.6 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_S | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q4_K_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q5_0 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q5_K_XXS | 0.7 GB | 1.2 GB | Fits | Get file → | |
| Q5_K_S | 0.7 GB | 1.2 GB | Fits | Get file → | |
| Q5_K_M | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q5_1 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q8_0 | 0.9 GB | 1.6 GB | Fits | Get file → | |
| F16 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| F32 | 3.4 GB | 4.4 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (file size 0.63 GB, memory 1.2 GB) is a good balance. With 4 GB VRAM, use Q3_K_XXS (0.47 GB, 1 GB). For the smallest footprint, Q2_K (0.45 GB, 1 GB) works but quality drops.
What GPU do you need for Fun CosyVoice3 0.5B 2512?
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 (1.7 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (3.4 GB file, about 4.4 GB in use).
Which Fun CosyVoice3 0.5B 2512 quant should you choose?
Q4_K_M is the usual starting point for Fun CosyVoice3 0.5B 2512: it balances file size and quality well. Here it is a 0.6 GB file.
The Q8_0 file is 0.9 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 0.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Fun CosyVoice3 0.5B 2512
How much VRAM does Fun CosyVoice3 0.5B 2512 need?
About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.6 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 Fun CosyVoice3 0.5B 2512 on an 8 GB GPU?
Yes, with F32: the 3.4 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Fun CosyVoice3 0.5B 2512 GGUF?
It depends on the quant: Q2_K is 0.4 GB, Q2_K_L is 0.5 GB, Q3_K_XXS is 0.5 GB, Q3_K_S is 0.5 GB, Q3_K_M is 0.5 GB, Q4_0 is 0.5 GB and 13 more.
Where can I download Fun CosyVoice3 0.5B 2512 GGUF?
The files are on Hugging Face in the Lourdle/Fun-CosyVoice3-0.5B-2512-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 Fun CosyVoice3 0.5B 2512 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 this model on 8 GB VRAM?
Yes, Q4_K_M or Q4_K_S use about 1.2 GB memory at 8 k context, fitting within 8 GB VRAM.
Does the model support voice cloning?
Yes, it supports zero‑shot voice cloning across multiple languages and dialects.
What is the recommended quant for near‑lossless quality?
Q8_0 provides near‑lossless listening quality with a 0.94 GB file size.