kartoffel orpheus 3b german natural needs about 4.4 GB of memory at Q8_0 (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 1.9 GB (Q4_K) to 6.6 GB (F16).
German natural speech model for CrispASR
Kartoffel-Orpheus 3B is a 3.3B‑parameter LLM fine‑tuned on natural German speech recordings. It uses the Orpheus architecture and is compatible with the CrispASR runtime and SNAC 24 kHz codec. The model is released under the llama3.2 license.
Good at
- German ASR with CrispASR
- Natural speech fine‑tuning
- SNAC 24 kHz codec integration
Limits
- No vision support
- Context length not specified
- Requires SNAC codec for audio output
Best for
- German voice‑to‑text pipelines
- CrispStrobe audio projects
- ASR with fixed German speaker roster
Who it’s for. Developers building German speech‑to‑text systems that use the CrispASR runtime. It is ideal for applications needing a natural‑speech fine‑tuned model with a German speaker roster and SNAC codec support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 1.9 GB | 2.6 GB | Fits | Get file → | |
| Q8_0 | 3.5 GB | 4.4 GB | Fits | Get file → | |
| F16 | 6.6 GB | 7.9 GB | Tight | Get file → |
For 8 GB VRAM use Q8_0 (file size 3.52 GB, estimated 4.4 GB memory at 8 k context). If VRAM is limited to 4 GB, Q4_K (1.87 GB, 2.6 GB memory) is an option, but Q8_0 is recommended for stable SNAC super‑frame handling.
What GPU do you need for kartoffel orpheus 3b german natural?
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 (1.9 GB file, about 2.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.5 GB file, about 4.4 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.6 GB file, about 7.9 GB in use).
Which kartoffel orpheus 3b german natural quant should you choose?
Q8_0 (3.5 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.
If memory is tight, the smallest file is Q4_K at 1.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about kartoffel orpheus 3b german natural
How much VRAM does kartoffel orpheus 3b german natural need?
About 4.4 GB at Q8_0 with an 8K context window. That is the 3.5 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 kartoffel orpheus 3b german natural 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 kartoffel orpheus 3b german natural GGUF?
It depends on the quant: Q4_K is 1.9 GB, Q8_0 is 3.5 GB, F16 is 6.6 GB.
Where can I download kartoffel orpheus 3b german natural GGUF?
The files are on Hugging Face in the cstr/kartoffel-orpheus-3b-german-natural-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 kartoffel orpheus 3b german natural use?
Hugging Face lists the license as llama3.2. 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 this model on 8 GB VRAM?
Yes, the Q8_0 quant uses 3.52 GB file size and needs about 4.4 GB memory at 8 k context, which fits in 8 GB VRAM.
Does this model support vision?
No, the model has no vision capabilities and is designed only for speech tasks.
What codec is required for audio output?
The model outputs SNAC 24 kHz codec tokens; you must pair it with the cstr/snac-24khz-GGUF codec to render audio.