nemo nano codec 22khz 1.89kbps 21.5fps needs about 0.6 GB of memory at F16 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
NVIDIA NeMo NanoCodec 1.89kbps 21.5fps – compact neural audio codec
The NeMo NanoCodec is a neural audio codec that uses finite scalar quantization and adversarial training with large speech language models. It offers high‑quality audio compression at 1.89kbps with a 21.5fps frame rate. The model is available under the NVIDIA Open Model License and can be used for commercial or non‑commercial purposes.
Good at
- Low‑bitrate audio compression
- High‑fidelity reconstruction at 21.5fps
- Integration with speech generation pipelines
Limits
- No vision support
- No language support listed
- Requires 8k context for memory estimate
Best for
- Audio compression for streaming
- Speech synthesis training
- Low‑bandwidth audio transmission
Who it’s for. Engineers and researchers building speech or audio applications that need efficient compression. The model is suitable for developers looking to embed a lightweight codec in production systems.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.1 GB | 0.6 GB | Fits | Get file → |
The F16 quantization file is 0.08 GB and requires about 0.6 GB of VRAM at 8k context. This is the only quant available, so it is the recommended choice for any memory budget above 0.6 GB.
What GPU do you need for nemo nano codec 22khz 1.89kbps 21.5fps?
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 (0.1 GB file, about 0.6 GB in use).
Which nemo nano codec 22khz 1.89kbps 21.5fps quant should you choose?
F16 (0.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about nemo nano codec 22khz 1.89kbps 21.5fps
How much VRAM does nemo nano codec 22khz 1.89kbps 21.5fps need?
About 0.6 GB at F16 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 nemo nano codec 22khz 1.89kbps 21.5fps on an 8 GB GPU?
Yes, with F16: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of nemo nano codec 22khz 1.89kbps 21.5fps GGUF?
It depends on the quant: F16 is 0.1 GB.
Where can I download nemo nano codec 22khz 1.89kbps 21.5fps GGUF?
The files are on Hugging Face in the nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does nemo nano codec 22khz 1.89kbps 21.5fps use?
Hugging Face lists the license as other. 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, the F16 quant requires approximately 0.6 GB of VRAM at 8k context, well within an 8 GB budget.
Is this model suitable for real‑time audio encoding?
Yes, with a 21.5fps frame rate it can encode audio in real time for many applications.
Does the model support multiple languages?
No language information is provided; the model is primarily an audio codec.