VibeVoice-Quants

Wildminder/VibeVoice-Quants

VibeVoice-Quants is a machine learning model from Wildminder. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.

Downloads · 30 days

89% of all-time downloads

All-time downloads

Public

Repo size

43.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors40.5 GB · 93%

At a glance

License: mit
Access: Public
Created: Aug 25, 2026
Updated: Oct 9, 2026
SHA: bfbcf05d

Base models

Model card

From the Hugging Face model README

VibeVoice Quants

Quantized VibeVoice checkpoints for the ComfyUI-VibeVoice node pack.

<a href="https://github.com/wildminder/ComfyUI-VibeVoice">Node repository</a> · <a href="https://github.com/wildminder/ComfyUI-VibeVoice/blob/main/README.md">Documentation</a> · <a href="https://github.com/wildminder/ComfyUI-VibeVoice/issues">Report an issue</a>

</div>

[!NOTE] These files are optional. The node downloads the official full-precision models on first run; point Load VibeVoice Model at a file from this repo to run quantized weights instead. No sidecar configs are needed — the node ships its own for every family here.

❖ Files

File	Format	Size	Base model
VibeVoice-1.5B-bf16	bf16	5.4 GB	microsoft/VibeVoice-1.5B
VibeVoice-1.5B-fp8_e4m3	fp8	2.8 GB	microsoft/VibeVoice-1.5B
VibeVoice-1.5B-int8-row-convrot-gs64	int8	3.1 GB	microsoft/VibeVoice-1.5B
VibeVoice-1.5B-q8_0	GGUF	3.2 GB	microsoft/VibeVoice-1.5B
VibeVoice-7B-fp8_e4m3	fp8	9.5 GB	vibevoice/VibeVoice-7B
VibeVoice-ASR-HF-bf16	bf16	16.7 GB	microsoft/VibeVoice-ASR-HF
VibeVoice-Realtime-0.5B-bf16	bf16	2.0 GB	microsoft/VibeVoice-Realtime-0.5B
VibeVoice-Realtime-0.5B-int8_block-simple-heur	int8	1.1 GB	microsoft/VibeVoice-Realtime-0.5B

⌬ Formats

Format	Storage	Notes
bf16	full precision	Reference quality; matches the official checkpoints.
fp8	8-bit float, per-block scales	~1.9× smaller than bf16; weights stay packed in memory at run time.
int8	8-bit integer, rowwise/blockwise	The `convrot` variant stores rotated weights; `simple-heur` is blockwise.
GGUF	q8_0, llama.cpp-style	Single file; needs the `gguf` package (`pip install gguf`).

Quantization metadata is embedded in each checkpoint, so the node detects the format and the architecture from the file itself — no manual setup.

⇩ How to use

Download a file into ComfyUI/models/diffusion_models/.
Wire Load VibeVoice Model → external_model on the TTS or ASR node — connected, it overrides the standard model_name dropdown.
Keep config_name on Auto-detect.

Full setup, node inputs and VRAM notes in the node documentation.

§ License

MIT, matching the base models. VibeVoice is Microsoft's.

License: mit
Created: Aug 25, 2026
Updated: Oct 9, 2026