dia 1.6b needs about 1.5 GB of memory at Q4_K (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.1 GB to 3.2 GB (F16).
Dia 1.6B: 1.6B‑parameter dialogue text‑to‑speech model
Dia is a 1.6B‑parameter text‑to‑speech model that generates expressive 44.1 kHz speech from text. It supports speaker tags [S1] and [S2] and can produce non‑verbal sounds such as laughter and coughing. The model is released under Apache‑2.0 and only supports English.
Good at
- Realistic dialogue generation
- Speaker‑tagged speech
- Non‑verbal sound synthesis
Limits
- No vision support
- Requires at least 8 k context
- Only English
Best for
- Creating dialogue‑based audio content
- Voice cloning demos
- Generating expressive podcast audio
Who it’s for. Developers building voice‑enabled applications who need realistic dialogue synthesis. Researchers experimenting with text‑to‑speech models and audio generation workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| F16 | 3.2 GB | 4.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K (file size 0.93 GB, estimated memory 1.5 GB). For 16 GB VRAM, Q8_0 (1.73 GB, 2.4 GB). For 32 GB VRAM, F16 (3.22 GB, 4.1 GB). Estimates are approximate.
What GPU do you need for dia 1.6b?
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 (1.7 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.2 GB file, about 4.1 GB in use).
Which dia 1.6b quant should you choose?
Q4_K (0.9 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 0.1 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 dia 1.6b
How much VRAM does dia 1.6b need?
About 1.5 GB at Q4_K with an 8K context window. That is the 0.9 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 dia 1.6b on an 8 GB GPU?
Yes, with F16: the 3.2 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of dia 1.6b GGUF?
It depends on the quant: file is 0.1 GB, Q4_K is 0.9 GB, Q8_0 is 1.7 GB, F16 is 3.2 GB.
Where can I download dia 1.6b GGUF?
The files are on Hugging Face in the cstr/dia-1.6b-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 dia 1.6b 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 Dia on 8 GB VRAM?
Yes, the Q4_K quant uses about 1.5 GB of VRAM at 8 k context.
Does Dia support multiple languages?
No, Dia currently supports only English generation.
Is there a CPU inference option?
CPU support is not yet available; Dia has been tested only on GPUs.