SE

SenseVoice Small

SensevoicesmallGGUF by handy-computerUpdated 2026-10-16
Download on Hugging Face
Parameters234M
Context—
Layers—
Architecturesensevoice
Smallest quant0.1 GB
Quick answer

SenseVoice Small needs about 0.7 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 6 quants, from 0.1 GB (Q4_K_M) to 0.9 GB (F32).

SenseVoice Small – lightweight multilingual speech‑to‑text model

SenseVoice Small is a 0.234 billion‑parameter speech foundation model. It supports ASR, language ID, emotion recognition, and audio event detection. The model runs as a single binary via llama.cpp / GGUF with built‑in VAD.

Good at

  • Fast inference – 70 ms for 10 s audio
  • Multilingual ASR – over 50 languages
  • Emotion and audio‑event detection

Limits

  • No GPU required, but limited to 8 k context
  • License is other – check usage terms
  • No streaming or translation support

Best for

  • Edge devices needing quick speech transcription
  • Multilingual voice assistants
  • Audio‑event monitoring

Who it’s for. Developers building lightweight speech‑to‑text services on CPUs. The model is ideal for edge deployments where GPU resources are unavailable and low latency is critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.1 GB 0.7 GB
Fits Get file →
Q5_K_M0.2 GB 0.7 GB
Fits Get file →
Q6_K0.2 GB 0.7 GB
Fits Get file →
Q8_00.3 GB 0.8 GB
Fits Get file →
F160.5 GB 1.0 GB
Fits Get file →
F320.9 GB 1.5 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M or Q5_K_M (0.15–0.17 GB) are suitable, using about 0.7 GB RAM at 8 k context. If more memory is available, Q8_0 (0.25 GB) gives higher precision. F16 and F32 are larger and need more RAM.

What GPU do you need for SenseVoice Small?

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

Which SenseVoice Small quant should you choose?

Q4_K_M is the usual starting point for SenseVoice Small: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.3 GB, about 1.7 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

Architecturesensevoice
Parameters234M

Source

Quantized byhandy-computer
Licenseother
Downloads (HF)24,741
Last updated2026-10-16

Frequently asked questions about SenseVoice Small

How much VRAM does SenseVoice Small need?

About 0.7 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 SenseVoice Small on an 8 GB GPU?

Yes, with F32: 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 SenseVoice Small GGUF?

It depends on the quant: Q4_K_M is 0.1 GB, Q5_K_M is 0.2 GB, Q6_K is 0.2 GB, Q8_0 is 0.3 GB, F16 is 0.5 GB, F32 is 0.9 GB.

Where can I download SenseVoice Small GGUF?

The files are on Hugging Face in the handy-computer/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 SenseVoice Small 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 SenseVoice Small on 8 GB VRAM?

Yes. The Q4_K_M and Q5_K_M quantizations fit comfortably, using roughly 0.7 GB of VRAM at 8 k context.

Does the model support streaming inference?

No. SenseVoice Small is a non‑streaming, single‑pass model.

What languages can it transcribe?

It supports over 50 languages, including Chinese, Cantonese, English, Japanese, and Korean.

Other GGUFs of SenseVoiceSmall

Similar models

Browse all →

More from handy-computer

All by handy-computer →

More Sensevoicesmall models

All Sensevoicesmall →

Other tiny models

All tiny models →