OR

Orpheus 3b FT Q8 0

OrpheusGGUF by lex-auUpdated 2025-03-24
Download on Hugging Face
Parameters3.78B
Context128K
Layers28
Architecturellama
Smallest quant4.0 GB
Quick answer

Orpheus 3b FT Q8 0 needs about 5.5 GB of memory at Q8_0 (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Orpheus 3b FT Q8 0 – 3B parameter Text-to-Speech model quantised to 8‑bit

Orpheus 3b FT Q8 0 is a 3.78 billion parameter Text-to-Speech model. It converts text into natural‑sounding 24kHz mono audio with multiple voices and emotion tags. The model is quantised to Q8_0 for efficient inference on consumer GPUs.

Good at

  • Natural‑sounding speech synthesis
  • Emotion‑aware voice output
  • CUDA‑optimised inference

Limits

  • No vision support
  • Requires 8 k context for memory estimate
  • License: apache‑2.0

Best for

  • Voice‑over generation
  • Interactive voice assistants
  • Audio content creation

Who it’s for. Developers building voice applications who need a compact, high‑quality TTS model. The 4.03 GB GGUF file fits on most consumer GPUs, and the 5.5 GB memory estimate at 8 k context is suitable for local inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.0 GB 5.5 GB
Fits Get file →

The only available quant is Q8_0, 4.03 GB in size. It requires approximately 5.5 GB of VRAM at 8 k context. For lower VRAM budgets, no other quantisations are provided, so Q8_0 is the recommended choice.

What GPU do you need for Orpheus 3b FT Q8 0?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.0 GB file, about 5.5 GB in use).

Which Orpheus 3b FT Q8 0 quant should you choose?

Q8_0 (4.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.78B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bylex-au
FamilyOrpheus
Licenseapache-2.0
Downloads (HF)2,472
Last updated2025-03-24

Frequently asked questions about Orpheus 3b FT Q8 0

How much VRAM does Orpheus 3b FT Q8 0 need?

About 5.5 GB at Q8_0 with an 8K context window. That is the 4.0 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 FT Q8 0 on an 8 GB GPU?

Yes, with Q8_0: the 4.0 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Orpheus 3b FT Q8 0 GGUF?

It depends on the quant: Q8_0 is 4.0 GB.

What context length does Orpheus 3b FT Q8 0 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 FT Q8 0 GGUF?

The files are on Hugging Face in the lex-au/Orpheus-3b-FT-Q8_0.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 FT Q8 0 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 FT Q8 0 on 8 GB VRAM?

Yes, the model requires about 5.5 GB of VRAM at 8 k context, so it fits comfortably on an 8 GB GPU.

Does this model support vision or multimodal input?

No, it is a text‑to‑speech model with no vision capabilities.

What inference servers can I use with this model?

It can be loaded into GPUStack, LM Studio, llama.cpp server, or any OpenAI‑compatible server.

Similar models

Browse all →

More from lex-au

All by lex-au →

More Orpheus models

All Orpheus →

Other small models

All small models →