diar streaming sortformer 4spk v2 needs about 0.7 GB of memory at Q8_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
Streaming Sortformer 4-speaker diarization model
The diar streaming sortformer 4spk v2 model performs speaker diarization in real time. It supports up to four speakers and is built from NVIDIA’s Sortformer architecture. The GGUF build is available in Q8_0 quantization.
Good at
- Real‑time speaker diarization
- Supports 4 speakers
- Fast-Conformer based encoder
Limits
- Only Q8_0 quant supported
- No vision or multimodal features
- Requires 8k context for memory estimate
Best for
- Live meeting transcription
- Voice assistant speaker recognition
- Real‑time call analytics
Who it’s for. Developers building real‑time audio processing pipelines that need accurate speaker separation. The model is suitable for integration with NeMo Voice Agent or similar frameworks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → |
For 8 GB VRAM, the Q8_0 file (0.15 GB) requires about 0.7 GB of VRAM at 8k context. This is well within the budget. No other quantizations are available for this model.
What GPU do you need for diar streaming sortformer 4spk v2?
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 Q8_0 (0.1 GB file, about 0.7 GB in use).
Which diar streaming sortformer 4spk v2 quant should you choose?
Q8_0 (0.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about diar streaming sortformer 4spk v2
How much VRAM does diar streaming sortformer 4spk v2 need?
About 0.7 GB at Q8_0 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 diar streaming sortformer 4spk v2 on an 8 GB GPU?
Yes, with Q8_0: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of diar streaming sortformer 4spk v2 GGUF?
It depends on the quant: Q8_0 is 0.1 GB.
Where can I download diar streaming sortformer 4spk v2 GGUF?
The files are on Hugging Face in the vibe-app/diar-streaming-sortformer-4spk-v2-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 diar streaming sortformer 4spk v2 use?
Hugging Face lists the license as cc-by-4.0. 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 this model on 8 GB VRAM?
Yes. The Q8_0 quantization uses approximately 0.7 GB of VRAM at 8k context, leaving ample headroom.
Does this model support more than four speakers?
No. The model is capped at four speakers as per the architecture.
What license applies to this model?
The model is licensed under cc-by-4.0, inherited from the parent model.