Audio Flamingo needs about 10.9 GB of memory at Q8_0 (a 9.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 5.5 GB (Q4_K) to 16.6 GB (BF16).
Audio Flamingo 3: Open large audio‑language model for speech, sound, and music
Audio Flamingo 3 is a fully open large audio‑language model that supports transcription, captioning, and audio reasoning. It processes audio in 30‑second windows with a 10‑minute total cap per sample. The model is available in GGUF format for audio.cpp and Transformers.
Good at
- Transcription and captioning
- Audio reasoning across speech, music, and sounds
- Multi‑turn audio dialogue
Limits
- No vision support
- Requires 8‑minute context limit
- Non‑commercial research use only
Best for
- Audio transcription tasks
- Audio question answering
- Multi‑turn audio chat
Who it’s for. Researchers and developers working on audio‑language applications who need an open, fully supported model for speech, music, and environmental sound understanding. The model is intended for non‑commercial research use only.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 5.5 GB | 6.6 GB | Fits | Get file → | |
| Q4_K | 5.5 GB | 6.6 GB | Fits | Get file → | |
| Q8_0 | 9.3 GB | 10.9 GB | Too big | Get file → | |
| Q8_0 | 9.3 GB | 10.9 GB | Too big | Get file → | |
| Q8_0 | 9.3 GB | 10.9 GB | Too big | Get file → | |
| BF16 | 16.5 GB | 19.0 GB | Too big | Get file → | |
| BF16 | 16.6 GB | 19.0 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q4_K GGUF (5.46 GB, ~6.6 GB memory at 8k context). For 12‑GB VRAM, use Q8_0 (9.31 GB, ~10.9 GB memory). For larger GPUs, BF16 (16.55 GB, ~19 GB memory) provides the highest precision.
What GPU do you need for Audio Flamingo?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q4_K (5.5 GB file, about 6.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.3 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.3 GB file, about 10.9 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.6 GB file, about 19.0 GB in use).
Which Audio Flamingo quant should you choose?
Q8_0 (9.3 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 5.5 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
Source
Frequently asked questions about Audio Flamingo
How much VRAM does Audio Flamingo need?
About 10.9 GB at Q8_0 with an 8K context window. That is the 9.3 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 Audio Flamingo on an 8 GB GPU?
Yes, with Q4_K: the 5.5 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Audio Flamingo GGUF?
It depends on the quant: Q4_K is 5.5 GB, Q4_K is 5.5 GB, Q8_0 is 9.3 GB, Q8_0 is 9.3 GB, Q8_0 is 9.3 GB, BF16 is 16.5 GB and 1 more.
Where can I download Audio Flamingo GGUF?
The files are on Hugging Face in the audio-cpp/Audio-Flamingo-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 Audio Flamingo use?
Hugging Face lists the license as other. 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 Audio Flamingo 3 on 8 GB VRAM?
Yes, the Q4_K quantized GGUF is 5.46 GB and requires about 6.6 GB of VRAM at 8k context.
Does Audio Flamingo 3 support vision tasks?
No, the model is audio‑only and does not provide vision capabilities.
Is Audio Flamingo 3 suitable for commercial deployment?
The model is licensed for non‑commercial research purposes only and is not intended for commercial use.