How much VRAM does VibeVoice-Realtime-0.5B need?

Q4_K is exactly 698,629,312 bytes (0.65 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

microsoft · audio tts

VibeVoice-Realtime-0.5B

microsoft/VibeVoice-Realtime-0.5B

VibeVoice-Realtime-0.5B at Q4_K is exactly 698,629,312 bytes (0.65 GiB / 0.70 GB) — an effective 5.492 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

1.0B

Architecture

vibevoice-tts

null layers

Context

—

native (config.json)

License

mit

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K	0.65 GiB	698,629,312	5.492	—	cstr
Q8_0	1.08 GiB	1,164,668,096	9.156	—	cstr
F16	1.90 GiB	2,038,490,752	16.025	—	cstr

Compare with

same modality, comparable size

vs Ace-Step1.5 vs Qwen3-TTS-12Hz-0.6B-Base vs OmniVoice vs orpheus-3b-0.1-ft vs VieNeu-TTS-0.3B vs neutts-air All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K at roughly 0.53 GiB. The real file is 0.65 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

—

Attention heads

—

KV heads

—

Head dim

—

Hidden size

—

Vocab

—

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does VibeVoice-Realtime-0.5B need?: Q4_K is exactly 698,629,312 bytes (0.65 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of VibeVoice-Realtime-0.5B should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.