MI

mimo tokenizer

MimoGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters649M
Context—
Layers—
Architecturemimo_tokenizer
Smallest quant0.4 GB
Quick answer

mimo tokenizer needs about 0.9 GB of memory at Q4_K (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU.

MiMo Audio Tokenizer encoder for audio-to-token conversion

MiMo Audio Tokenizer is a 32‑layer transformer encoder with 600M parameters. It converts 24kHz audio into RVQ tokens at 25 Hz. The model is released under the MIT license.

Good at

  • Fast audio tokenization
  • High‑quality RVQ encoding
  • Low‑latency 25 Hz output

Limits

  • Only encoder; no decoder or vocoder
  • Requires 8 k context for memory estimate
  • No vision or text generation capabilities

Best for

  • ASR pipelines needing tokenization
  • Audio preprocessing for language models
  • Real‑time speech encoding

Who it’s for. Engineers building speech recognition or audio‑language models who need a lightweight encoder. The model is suitable for developers working with MiMo‑V2.5‑ASR or similar pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.4 GB 0.9 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K variant (0.4 GB file). It requires approximately 0.9 GB of VRAM at 8 k context. Larger VRAM can accommodate higher‑precision quantisations if available.

What GPU do you need for mimo tokenizer?

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 Q4_K (0.4 GB file, about 0.9 GB in use).

Which mimo tokenizer quant should you choose?

Q4_K (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

Architecturemimo_tokenizer
Parameters649M

Source

Quantized bycstr
FamilyMimo
Licensemit
Downloads (HF)1,083
Last updated2026-08-02

Frequently asked questions about mimo tokenizer

How much VRAM does mimo tokenizer need?

About 0.9 GB at Q4_K 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 mimo tokenizer on an 8 GB GPU?

Yes, with Q4_K: the 0.4 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 mimo tokenizer GGUF?

It depends on the quant: Q4_K is 0.4 GB.

Where can I download mimo tokenizer GGUF?

The files are on Hugging Face in the cstr/mimo-tokenizer-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 mimo tokenizer 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 MiMo Audio Tokenizer on 8 GB VRAM?

Yes, the Q4_K variant uses about 0.9 GB of VRAM at 8 k context, fitting comfortably in 8 GB.

Does this model support text generation?

No, it only provides audio tokenization; a separate decoder or LLM is needed for generation.

What license applies to this model?

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

Other GGUFs of MiMo-Audio-Tokenizer

Similar models

Browse all →

More from cstr

All by cstr →

More Mimo models

All Mimo →

Other tiny models

All tiny models →