How much VRAM does VieNeu-TTS need?

Q4_0 is exactly 416,538,624 bytes (0.39 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is VieNeu-TTS's KV cache?

0.38 GiB at 32K context with an f16 cache, computed per layer from the model's architecture. Quantizing the cache to q8_0 roughly halves it.

pnnbao-ump · audio tts

VieNeu-TTS

pnnbao-ump/VieNeu-TTS

VieNeu-TTS at Q4_0 is exactly 416,538,624 bytes (0.39 GiB / 0.42 GB) — an effective 6.027 bits per weight, not the nominal 4. Its KV cache at 32K is 0.38 GiB.

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

Parameters

553M

Architecture

qwen2

24 layers

Context

32,768

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_0	0.39 GiB	416,538,624	6.027	—	pnnbao-ump

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.05 GiB	0.05 GiB	—	24 / 0 / 0
8,192	0.09 GiB	0.09 GiB	—	24 / 0 / 0
16,384	0.19 GiB	0.19 GiB	—	24 / 0 / 0
32,768	0.38 GiB	0.38 GiB	—	24 / 0 / 0
65,536	0.75 GiB	0.75 GiB	—	24 / 0 / 0
131,072	1.50 GiB	1.50 GiB	—	24 / 0 / 0

Compare with

same modality, comparable size

vs Qwen3-TTS-12Hz-0.6B-Base vs OmniVoice vs orpheus-3b-0.1-ft vs VieNeu-TTS-0.3B vs neutts-air 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_0 at roughly 0.29 GiB. The real file is 0.39 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

896

Vocab

217,652

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

false

Questions people ask

How much VRAM does VieNeu-TTS need?: Q4_0 is exactly 416,538,624 bytes (0.39 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is VieNeu-TTS's KV cache?: 0.38 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.
Which quantization of VieNeu-TTS 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.