AU

Audar TTS V1 Turbo

AudarGGUF by audaraiUpdated 2026-07-07
Download on Hugging Face
Parameters1.64B
Context32K
Layers28
Architectureqwen2
Smallest quant1.1 GB
Quick answer

Audar TTS V1 Turbo needs about 1.8 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.1 GB (Q4_K_M) to 1.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Audar TTS V1 Turbo – Arabic‑first, bilingual text‑to‑speech model

Audar TTS V1 Turbo is a 1.64B‑parameter speech model that balances production quality with efficiency. It supports Arabic and English, and can clone any voice from a 5–15 second clip without per‑speaker fine‑tuning. The model is distributed as GGUF quantizations for llama.cpp.

Good at

  • Arabic‑first bilingual TTS
  • Zero‑shot voice cloning
  • Efficient 1.64B parameter size

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License limited to research and small commercial use

Best for

  • Local deployment of Arabic‑English TTS
  • Voice cloning from short reference clips
  • Low‑latency speech synthesis

Who it’s for. Developers building Arabic‑first or bilingual TTS applications who need a lightweight, open‑source model. Ideal for research labs and small businesses with limited GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.1 GB 1.8 GB
Fits Get file →
Q5_K_M1.2 GB 1.9 GB
Fits Get file →
Q8_01.8 GB 2.5 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K_M quant (1.07 GB, ~1.8 GB memory at 8k context). If 12 GB VRAM is available, Q5_K_M (1.21 GB, ~1.9 GB memory) offers higher quality. The Q8_0 quant (1.75 GB, ~2.5 GB memory) is best for the highest fidelity when memory permits.

What GPU do you need for Audar TTS V1 Turbo?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 (1.8 GB file, about 2.5 GB in use).

Which Audar TTS V1 Turbo quant should you choose?

Q4_K_M is the usual starting point for Audar TTS V1 Turbo: it balances file size and quality well. Here it is a 1.1 GB file.

The Q8_0 file is 1.8 GB, about 1.6 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

Architectureqwen2
Parameters1.64B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized byaudarai
FamilyAudar
Licenseother
Downloads (HF)3,839
Last updated2026-07-07

Frequently asked questions about Audar TTS V1 Turbo

How much VRAM does Audar TTS V1 Turbo need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Audar TTS V1 Turbo on an 8 GB GPU?

Yes, with Q8_0: 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 Audar TTS V1 Turbo GGUF?

It depends on the quant: Q4_K_M is 1.1 GB, Q5_K_M is 1.2 GB, Q8_0 is 1.8 GB.

What context length does Audar TTS V1 Turbo support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download Audar TTS V1 Turbo GGUF?

The files are on Hugging Face in the audarai/Audar-TTS-V1-Turbo repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Audar TTS V1 Turbo 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 Audar TTS V1 Turbo on 8 GB VRAM?

Yes, the Q4_K_M quant uses 1.07 GB and requires about 1.8 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support other languages besides Arabic and English?

The model is fully bilingual with Arabic and English; no other languages are supported.

Is there a phonemizer or G2P for Arabic?

No phonemizer or per‑language G2P is included; Arabic dialects and code‑switching are handled directly from data.

Similar models

Browse all →

More from audarai

All by audarai →

More Audar models

All Audar →

Other tiny models

All tiny models →