OR

orpheus 3b 0.1 ft

OrpheusGGUF by cstrUpdated 2026-08-02
Download on Hugging Face
Parameters3.3B
Context—
Layers—
Architecturecrispasr.reference
Smallest quant0.0 GB
Quick answer

orpheus 3b 0.1 ft needs about 3.4 GB of memory at Q4_K (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB to 6.6 GB (F16).

Orpheus 3B 0.1 ft – a 3.3B Llama‑3.2‑Instruct talker for low‑latency speech

Orpheus 3B 0.1 ft is a 3.3B parameter Llama‑3.2‑Instruct model fine‑tuned to emit SNAC 24 kHz codec tokens. It delivers human‑like speech with natural intonation and emotion, supports zero‑shot voice cloning, and streams audio with ~200 ms latency. The model is released under apache‑2.0.

Good at

  • Low‑latency streaming speech
  • Zero‑shot voice cloning
  • Emotion tagging via simple tags

Limits

  • No vision support
  • Requires SNAC codec for audio rendering
  • Sub‑Q8 quants may produce gibberish

Best for

  • Embedded TTS in edge devices
  • Real‑time voice assistants
  • Audio generation pipelines

Who it’s for. Developers building speech applications that need a lightweight, open‑source TTS model. The model is suitable for projects that can integrate the SNAC codec and manage the 8 k context length requirement.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
Q4_K2.6 GB 3.4 GB
Fits Get file →
Q8_04.0 GB 4.9 GB
Fits Get file →
F166.6 GB 7.9 GB
Tight Get file →

For 8 GB VRAM use Q4_K (file size 2.56 GB, estimated 3.4 GB memory at 8 k context). For 12 GB VRAM use Q8_0 (file size 3.97 GB, estimated 4.9 GB memory). For 16 GB VRAM use F16 (file size 6.61 GB, estimated 7.9 GB memory). The Q8_0 quant is the safe default for best audio quality.

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 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 Q4_K (2.6 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.0 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.6 GB file, about 7.9 GB in use).

Which orpheus 3b 0.1 ft quant should you choose?

Q4_K (2.6 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 0.0 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

Architecturecrispasr.reference
Parameters3.3B

Source

Quantized bycstr
FamilyOrpheus
Licenseapache-2.0
Downloads (HF)1,090
Last updated2026-08-02

Frequently asked questions about orpheus 3b 0.1 ft

How much VRAM does orpheus 3b 0.1 ft need?

About 3.4 GB at Q4_K with an 8K context window. That is the 2.6 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 F16: the 6.6 GB file needs about 7.9 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: file is 0.0 GB, Q4_K is 2.6 GB, Q8_0 is 4.0 GB, F16 is 6.6 GB.

Where can I download orpheus 3b 0.1 ft GGUF?

The files are on Hugging Face in the cstr/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, the Q4_K quant uses about 3.4 GB memory at 8 k context, fitting comfortably in 8 GB VRAM.

Does the model support multiple languages?

The model is trained on English and does not include other languages.

Do I need special hardware to use the SNAC codec?

No, the SNAC codec is available as a GGUF model and can run on standard CPU or GPU setups.

Other GGUFs of orpheus-3b-0.1-ft

Similar models

Browse all →

More from cstr

All by cstr →

More Orpheus models

All Orpheus →

Other tiny models

All tiny models →