codec.cpp needs about 0.6 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.1 GB (Q4_K_M) to 0.3 GB (F32).
codec.cpp – compact neural audio codec
codec.cpp is a small neural audio codec that converts speech to discrete tokens and back. It runs offline on CPU or GPU and supports multiple precisions. The model is 0.0739 billion parameters.
Good at
- Audio compression
- Speech tokenization
- Offline CPU/GPU decoding
Limits
- No vision support
- License is other
- No trained context tokens
Best for
- Local TTS pipelines
- Audio preprocessing
- Embedded audio applications
Who it’s for. Developers building TTS or audio processing systems that require a lightweight codec. The model is suitable for edge devices and offline use cases.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| — | 0.1 GB | 0.7 GB | Fits | Get file → | |
| — | 0.1 GB | 0.7 GB | Fits | Get file → | |
| — | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F32 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F32 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F32 | 0.3 GB | 0.9 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K_M 0.05 GB file uses about 0.6 GB memory at 8 k context. Q5_K_M 0.06 GB and Q8_0 0.08 GB are similar. For higher quality, use Q8_0 0.08 GB or F32 0.27 GB with ~0.8 GB memory.
What GPU do you need for codec.cpp?
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 F32 (0.3 GB file, about 0.9 GB in use).
Which codec.cpp quant should you choose?
Q4_K_M is the usual starting point for codec.cpp: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about codec.cpp
How much VRAM does codec.cpp need?
About 0.6 GB at Q4_K_M 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 codec.cpp on an 8 GB GPU?
Yes, with F32: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of codec.cpp GGUF?
It depends on the quant: Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q8_0 is 0.1 GB, Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q8_0 is 0.1 GB and 9 more.
Where can I download codec.cpp GGUF?
The files are on Hugging Face in the BricksDisplay/codec.cpp-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 codec.cpp 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 codec.cpp on 8 GB VRAM?
Yes. The Q4_K_M 0.05 GB quant uses about 0.6 GB memory at 8 k context, well within 8 GB VRAM.
What precision should I choose for best quality?
Use the F32 quant (0.27 GB) for full precision, but it requires ~0.8 GB memory at 8 k context.
Is codec.cpp suitable for real‑time TTS?
Yes, it runs offline on CPU or GPU and is designed for TTS pipelines, converting tokens to audio in real time.