How much VRAM does VoxCPM-0.5B need?

Q4_K is exactly 2,627,392,512 bytes (2.45 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

openbmb · audio tts

VoxCPM-0.5B

openbmb/VoxCPM-0.5B

VoxCPM-0.5B at Q4_K is exactly 2,627,392,512 bytes (2.45 GiB / 2.63 GB) — an effective 28.888 bits per weight, not the nominal 4.

From the file· summed from 3 file(s)From the file· KV per layer

Parameters

728M

Architecture

llama

null layers

Context

—

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K3 shards	2.45 GiB	2,627,392,512	28.888	—	bluryar
Q8_03 shards	4.08 GiB	4,378,822,240	—	—	bluryar
F323 shards	14.91 GiB	16,009,379,936	—	—	bluryar
F1612 shards	21.80 GiB	23,407,405,184	—	—	bluryar

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 s2-pro vs Fun-CosyVoice3-0.5B-2512 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 0.38 GiB. The real file is 2.45 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 VoxCPM-0.5B need?: Q4_K is exactly 2,627,392,512 bytes (2.45 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of VoxCPM-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.