# Can the RTX A4000 run ZONOS3-Mini-hf?

> Yes. The RTX A4000 runs ZONOS3-Mini-hf fully in VRAM at FP16 / BF16 (about 2.8 GB of 16 GB).

RTX A4000: 16 GB (16 GB usable), 448 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q4_K_M | Small loss | 1.21 | fits | — |
| Q8_0 | Lossless | 1.74 | fits | — |
| F16 (pick) | Lossless | 2.83 | fits | — |

## Run it

Run with the text-to-speech pipeline (transformers):

```python
from transformers import pipeline

pipe = pipeline("text-to-speech", model="Zyphra/ZONOS3-Mini-hf")
result = pipe("Self-hosting puts you in control of your data.")
print(result)
```


## TTS models that fit comfortably

- [Qwen/Qwen3-TTS-12Hz-0.6B-Base](https://selfhost.directory/models/qwen/qwen3-tts-12hz-0.6b-base/on/rtx-a4000): F16 ≈2.54 GB
- [microsoft/VibeVoice-Realtime-0.5B](https://selfhost.directory/models/microsoft/vibevoice-realtime-0.5b/on/rtx-a4000): F16 ≈2.77 GB
- [Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice](https://selfhost.directory/models/qwen/qwen3-tts-12hz-0.6b-customvoice/on/rtx-a4000): F16 ≈2.52 GB
- [inclusionAI/Ming-3.0-tts-0.5B](https://selfhost.directory/models/inclusionai/ming-3.0-tts-0.5b/on/rtx-a4000): F16 ≈3.81 GB
- [k2-fsa/OmniVoice](https://selfhost.directory/models/k2-fsa/omnivoice/on/rtx-a4000): F16 ≈1.87 GB
- [sesame/csm-1b](https://selfhost.directory/models/sesame/csm-1b/on/rtx-a4000): F16 ≈3.97 GB

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/rtx-4060): F16
- [Apple M4 (16 GB)](https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/apple-m4-16gb): F16
- [Radeon RX 6700 XT](https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/rx-6700-xt): F16
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/rtx-3060): F16
- [Arc B580](https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/arc-b580): F16
- [Tesla T4](https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/tesla-t4): F16
- [Arc A770 16GB](https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/arc-a770): F16
- [Radeon RX 7800 XT](https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/rx-7800-xt): F16

---
Model: https://selfhost.directory/models/zyphra/zonos3-mini-hf. GPU: https://selfhost.directory/models/gpus/rtx-a4000. Source: https://selfhost.directory/models/zyphra/zonos3-mini-hf/on/rtx-a4000