SE

SenseVoiceSmall

SensevoicesmallGGUF by FunAudioLLMUpdated 2026-06-21
Download on Hugging Face
Parameters234M
Context—
Layers—
Architecturesensevoice-small
Smallest quant0.3 GB
Quick answer

SenseVoiceSmall needs about 1.0 GB of memory at F16 (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.3 GB to 0.9 GB.

SenseVoiceSmall – lightweight multilingual ASR for CPU edge

SenseVoiceSmall is a 0.234 billion‑parameter ASR model built for the FunASR llama.cpp runtime. It supports multilingual transcription with language, emotion, and event tags. The model runs at roughly 20× real‑time on a CPU.

Good at

  • Fast CPU inference
  • Multilingual transcription
  • Tag‑aware output

Limits

  • No vision support
  • Requires FunASR runtime
  • No Python integration

Best for

  • Edge devices with limited VRAM
  • Real‑time speech transcription
  • Low‑latency voice assistants

Who it’s for. Developers building CPU‑only speech recognition solutions or embedded devices that need quick, tag‑aware transcription without Python dependencies.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.3 GB 0.8 GB
Fits Get file →
F160.5 GB 1.0 GB
Fits Get file →
—0.9 GB 1.5 GB
Fits Get file →

For 8 GB VRAM use the F16 quant (0.47 GB, 1 GB memory at 8k context). If more memory is available, the 0.94 GB file (1.5 GB memory) offers higher precision. The 0.25 GB file is the smallest but has unknown quantization.

What GPU do you need for SenseVoiceSmall?

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 the main file (0.9 GB file, about 1.5 GB in use).

Which SenseVoiceSmall quant should you choose?

F16 (0.5 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.

If memory is tight, the smallest file is the first one in the table at 0.3 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturesensevoice-small
Parameters234M

Source

Quantized byFunAudioLLM
Licenseapache-2.0
Downloads (HF)5,221
Last updated2026-06-21

Frequently asked questions about SenseVoiceSmall

How much VRAM does SenseVoiceSmall need?

About 1.0 GB at F16 with an 8K context window. That is the 0.5 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 SenseVoiceSmall on an 8 GB GPU?

Yes, with the smaller files: the 0.9 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SenseVoiceSmall GGUF?

It depends on the quant: file is 0.3 GB, F16 is 0.5 GB, file is 0.9 GB.

Where can I download SenseVoiceSmall GGUF?

The files are on Hugging Face in the FunAudioLLM/SenseVoiceSmall-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 SenseVoiceSmall 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.

Can I run SenseVoiceSmall on 8 GB VRAM?

Yes, the F16 quant file is 0.47 GB and requires about 1 GB of VRAM at 8k context, which fits easily in 8 GB.

Does this model support vision tasks?

No, SenseVoiceSmall is an audio‑only model and has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from FunAudioLLM

All by FunAudioLLM →

More Sensevoicesmall models

All Sensevoicesmall →

Other tiny models

All tiny models →