What hardware does Orpheus 3B run on?

Tuned builds: NVIDIA H100 SXM5. plowrt also runs them on H100 NVL, H200 SXM.

Does Orpheus 3B fit on one GPU?

Yes. The sm90a-h100-tp1 build runs on one NVIDIA H100 SXM5.

Can I run Orpheus 3B on AMD?

Not with a tuned build yet. Today's builds are for NVIDIA.

What context length does Orpheus 3B support?

The upstream model supports 131,072 tokens. Our builds serve up to 2,048.

What license is Orpheus 3B under?

Apache-2.0. Check the checkpoint's license on Hugging Face before commercial use.

How do I run Orpheus 3B?

Install plowrt, then run plowrt load orpheus --fetch-weights and plowrt serve --model orpheus --port 8080. It serves an OpenAI-compatible API.

Text to speech 3B 128k native context bf16 Apache-2.0

Orpheus 3B

Canopy Labs' Orpheus 3B, a Llama-based codec LM with a SNAC decoder, served with the same codec-LM contract as Veena.

unsloth/orpheus-3b-0.1-ft

Specs

Developer: Canopy Labs
Parameters: 3B
Task: Text to speech
Context: 131,072 tokens upstream, 2,048 served by our builds
Precisions: bf16
License: Apache-2.0
Checkpoint: unsloth/orpheus-3b-0.1-ft
Updated: 29 Oct 2026

Where it runs Each build is tuned for one part. plowrt runs it beyond that.

Tuned for

NVIDIA H100 SXM5

Runs as-is on H100 NVL, H200 SXM

Elsewhere plowrt still runs the model on other NVIDIA, AMD and Apple hardware, without this build’s tuning: expect lower throughput.

Run it An OpenAI-compatible server on your own machine.

plowrt 0.1.3 Install, pull, serve, call

curl -fsSL https://pdist.infervisor.ai/install.sh | sh

Install

```
plowrt load orpheus --fetch-weights
```
Pull with weights

plowrt serve --model orpheus --port 8080

Serve

curl -s http://127.0.0.1:8080/v1/audio/speech \
  -H 'content-type: application/json' \
  -d '{"model":"orpheus","input":"Hello from plow.","voice":"tara"}' -o out.wav

Try it

Builds `plowrt load` picks the closest fit for your machine.

NVIDIA H100 SXM5 80 GiB, also H100 NVL, H200 SXM bf16 1 GPU 2k Published

plowrt load infervisor/orpheus:sm90a-h100-tp1 --fetch-weights

This build only

Target: sm90a-h100-tp1 , tuned on NVIDIA H100 SXM5; runs as-is on H100 NVL, H200 SXM; other hardware runs it untuned
Checkpoint: unsloth/orpheus-3b-0.1-ft
Published: 29 Oct 2026
Compiled by: plowc 0.1.3 , from this recipe

About

The H100 label carries the Hopper decode knobs (decode cuBLASLt, FA fold, dense tune); the L40S label is the same contract without them. Both ship the lowered codec packet.

Questions

What hardware does Orpheus 3B run on?: Tuned builds: NVIDIA H100 SXM5. plowrt also runs them on H100 NVL, H200 SXM.
Does Orpheus 3B fit on one GPU?: Yes. The sm90a-h100-tp1 build runs on one NVIDIA H100 SXM5.
Can I run Orpheus 3B on AMD?: Not with a tuned build yet. Today's builds are for NVIDIA.
What context length does Orpheus 3B support?: The upstream model supports 131,072 tokens. Our builds serve up to 2,048.
What license is Orpheus 3B under?: Apache-2.0. Check the checkpoint's license on Hugging Face before commercial use.
How do I run Orpheus 3B?: Install plowrt, then run plowrt load orpheus --fetch-weights and plowrt serve --model orpheus --port 8080. It serves an OpenAI-compatible API.