MOSS Transcribe Diarize needs about 1.8 GB of memory at Q4_K (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB to 1.8 GB (F16).
0.9B end‑to‑end audio transcription and diarization
MOSS Transcribe Diarize 0.9B is an end‑to‑end audio understanding model. It performs long‑form transcription, speaker‑aware diarization, timestamps, and acoustic event awareness in a single pass. The model supports over 50 languages and audio up to 90 minutes.
Good at
- Long‑form multi‑speaker transcription
- Speaker‑aware diarization with anonymous labels
- Acoustic event annotations
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Meeting transcription
- Podcast subtitle generation
- Video lecture captioning
Who it’s for. Developers needing a single model for transcription and diarization. Researchers building downstream audio‑analysis pipelines. Content creators producing subtitles for long videos.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K | 1.2 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 1.4 GB | 2.1 GB | Fits | Get file → | |
| F16 | 1.8 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K (file size 1.19 GB, estimated 1.8 GB memory). For 12 GB VRAM use Q8_0 (1.41 GB, 2.1 GB memory). For 16 GB VRAM use F16 (1.82 GB, 2.5 GB memory). The unknown quant is 0.02 GB but memory estimate is 0.5 GB at 8k context.
What GPU do you need for MOSS Transcribe Diarize?
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 F16 (1.8 GB file, about 2.5 GB in use).
Which MOSS Transcribe Diarize quant should you choose?
Q4_K (1.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.0 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
Source
Frequently asked questions about MOSS Transcribe Diarize
How much VRAM does MOSS Transcribe Diarize need?
About 1.8 GB at Q4_K with an 8K context window. That is the 1.2 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 MOSS Transcribe Diarize on an 8 GB GPU?
Yes, with F16: the 1.8 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MOSS Transcribe Diarize GGUF?
It depends on the quant: file is 0.0 GB, Q4_K is 1.2 GB, Q8_0 is 1.4 GB, F16 is 1.8 GB.
Where can I download MOSS Transcribe Diarize GGUF?
The files are on Hugging Face in the cstr/MOSS-Transcribe-Diarize-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 MOSS Transcribe Diarize 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 MOSS Transcribe Diarize on 8 GB VRAM?
Yes, the Q4_K quant requires about 1.8 GB memory at 8k context, fitting within 8 GB VRAM.
Does the model support Chinese?
Yes, the subtitle Web UI supports Simplified Chinese and English.
Is the model open source?
Yes, it is released under the Apache‑2.0 license.