FU

npu cosyvoice

FunGGUF by billchen42Updated 2026-10-21
Download on Hugging Face
Parameters494M
Context32K
Layers24
Architectureqwen2
Smallest quant0.4 GB
Quick answer

npu cosyvoice needs about 1.0 GB of memory at Q4_0 (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

npu cosyvoice is a 494M-parameter Fun model in GGUF format, quantized by billchen42. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.4 GB (Q4_0) to 0.4 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.4 GB 1.0 GB
Fits Get file →

What GPU do you need for npu cosyvoice?

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 Q4_0 (0.4 GB file, about 1.0 GB in use).

Which npu cosyvoice quant should you choose?

Q4_0 (0.4 GB) is the middle option in this repository. 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

Architectureqwen2
Parameters494M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized bybillchen42
FamilyFun
Licenseapache-2.0
Downloads (HF)91
Last updated2026-10-21

Frequently asked questions about npu cosyvoice

How much VRAM does npu cosyvoice need?

About 1.0 GB at Q4_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 npu cosyvoice on an 8 GB GPU?

Yes, with Q4_0: the 0.4 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of npu cosyvoice GGUF?

It depends on the quant: Q4_0 is 0.4 GB.

What context length does npu cosyvoice support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download npu cosyvoice GGUF?

The files are on Hugging Face in the billchen42/npu-cosyvoice repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does npu cosyvoice 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.

Other GGUFs of Fun-CosyVoice3-0.5B-2512

Similar models

Browse all →

More Fun models

All Fun →

Other tiny models

All tiny models →