Orpheus-3B-0.1-Ft needs about 3.5 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 26 quants, from 1.0 GB (IQ1_S) to 6.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Orpheus‑3B‑0.1‑Ft: 3B Llama‑based TTS model for human‑like speech
Orpheus‑3B‑0.1‑Ft is a 3‑billion‑parameter Llama‑based text‑to‑speech model. It delivers natural intonation, emotion, and rhythm with low latency. The model is released under Apache‑2.0 and supports zero‑shot voice cloning.
Good at
- Human‑like speech synthesis
- Zero‑shot voice cloning
- Emotion control via tags
Limits
- Large context size (131072 tokens) requires significant VRAM
- No vision or multimodal support
- Requires sufficient RAM for inference
Best for
- Real‑time TTS applications
- Voice cloning for virtual assistants
- Emotion‑aware narration
Who it’s for. Developers building speech‑enabled applications who need high‑quality, expressive TTS. The model is suitable for research and production use where open‑source licensing is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ1_M | 1.0 GB | 2.5 GB | Fits | Get file → | |
| IQ2_XXS | 1.1 GB | 2.5 GB | Fits | Get file → | |
| IQ2_M | 1.3 GB | 2.8 GB | Fits | Get file → | |
| IQ3_XXS | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q2_K_L | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q2_K_XL | 1.5 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_S | 1.6 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 1.8 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_XL | 1.8 GB | 3.3 GB | Fits | Get file → | |
| IQ4_XS | 1.9 GB | 3.3 GB | Fits | Get file → | |
| IQ4_NL | 2.0 GB | 3.4 GB | Fits | Get file → | |
| Q4_0 | 2.0 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 2.0 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_XL | 2.1 GB | 3.6 GB | Fits | Get file → | |
| Q4_1 | 2.2 GB | 3.6 GB | Fits | Get file → | |
| Q5_K_S | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_XL | 2.4 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.7 GB | 4.2 GB | Fits | Get file → | |
| Q6_K_XL | 3.1 GB | 4.5 GB | Fits | Get file → | |
| Q8_0 | 3.5 GB | 5.0 GB | Fits | Get file → | |
| Q8_K_XL | 4.4 GB | 5.8 GB | Fits | Get file → | |
| F16 | 6.6 GB | 8.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (2 GB file, ~3.4 GB VRAM at 8 k context). For 12 GB VRAM, Q5_K_M (2.4 GB file, ~3.8 GB VRAM). For 16 GB VRAM, Q6_K (2.72 GB file, ~4.2 GB VRAM). Estimates are approximate.
What GPU do you need for Orpheus-3B-0.1-Ft?
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 Q5_K_XL (2.4 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_K_XL (4.4 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_K_XL (4.4 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (6.6 GB file, about 8.1 GB in use).
Which Orpheus-3B-0.1-Ft quant should you choose?
Q4_K_M is the usual starting point for Orpheus-3B-0.1-Ft: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.5 GB, about 1.7 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.
If memory is tight, the smallest file is IQ1_S at 1.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Orpheus-3B-0.1-Ft
How much VRAM does Orpheus-3B-0.1-Ft need?
About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Orpheus-3B-0.1-Ft on an 8 GB GPU?
Yes, with Q8_K_XL: the 4.4 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Orpheus-3B-0.1-Ft GGUF?
It depends on the quant: IQ1_S is 1.0 GB, IQ1_M is 1.0 GB, IQ2_XXS is 1.1 GB, IQ2_M is 1.3 GB, IQ3_XXS is 1.4 GB, Q2_K is 1.4 GB and 20 more.
What context length does Orpheus-3B-0.1-Ft support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Orpheus-3B-0.1-Ft GGUF?
The files are on Hugging Face in the unsloth/orpheus-3b-0.1-ft-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 Orpheus-3B-0.1-Ft 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 Orpheus‑3B‑0.1‑Ft on 8 GB VRAM?
Yes, using a Q4_K_S or Q4_K_M quantization will fit within 8 GB VRAM with about 3.4 GB usage.
Does this model support image input?
No, it is a text‑to‑speech model with no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.