WA

WavTokenizer Large Speech 75token

WavtokenizerGGUF by ggml-orgUpdated 2025-01-10
Download on Hugging Face
Parameters65M
Context8K
Layers12
Architecturewavtokenizer-dec
Smallest quant0.1 GB
Quick answer

WavTokenizer Large Speech 75token needs about 1.1 GB of memory at Q5_1 (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 (Q5_1) to 0.1 GB (F16).

WavTokenizer Large Speech 75token – 65 M parameters, 8192‑token context

WavTokenizer Large Speech 75token is a discrete audio codec model with 65 billion parameters. It supports 8192 context tokens and is released under the MIT license. The model is available in Q5_1 and F16 quantizations.

Good at

  • Discrete audio encoding
  • High token throughput
  • Low‑memory inference

Limits

  • No vision support
  • Limited to audio tasks
  • Requires 8 k context for full performance

Best for

  • Audio transcription preprocessing
  • Speech embedding generation
  • Audio data compression

Who it’s for. Developers building audio‑centric language models or speech processing pipelines. The model is suitable for researchers needing a lightweight codec for large‑scale audio datasets.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_10.1 GB 1.1 GB
Fits Get file →
F160.1 GB 1.1 GB
Fits Get file →

For 8 GB VRAM, use Q5_1 (0.07 GB file, ~1.1 GB memory). For higher precision, F16 (0.13 GB file, ~1.1 GB memory) fits within the same VRAM budget. Memory estimates are approximate.

What GPU do you need for WavTokenizer Large Speech 75token?

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 F16 (0.1 GB file, about 1.1 GB in use).

Which WavTokenizer Large Speech 75token quant should you choose?

Q5_1 (0.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewavtokenizer-dec
Parameters65M
Layers12
Trained context8,192 tokens
KV cache (fp16)60 KB per token

Source

Quantized byggml-org
Licensemit
Downloads (HF)1,687
Last updated2025-01-10

Frequently asked questions about WavTokenizer Large Speech 75token

How much VRAM does WavTokenizer Large Speech 75token need?

About 1.1 GB at Q5_1 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 WavTokenizer Large Speech 75token on an 8 GB GPU?

Yes, with F16: the 0.1 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WavTokenizer Large Speech 75token GGUF?

It depends on the quant: Q5_1 is 0.1 GB, F16 is 0.1 GB.

What context length does WavTokenizer Large Speech 75token support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.5 GB at 8K.

Where can I download WavTokenizer Large Speech 75token GGUF?

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

What license does WavTokenizer Large Speech 75token use?

Hugging Face lists the license as mit. 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 Q5_1 quantization requires about 1.1 GB of VRAM at 8 k context, fitting comfortably in 8 GB.

Does this model support vision tasks?

No, it is designed solely for audio processing and does not include vision capabilities.

What license applies to this model?

The model is released under the MIT license, allowing free use and modification.

Similar models

Browse all →

More from ggml-org

All by ggml-org →

Other tiny models

All tiny models →