How much VRAM does neutts-air need?

Q4_K_M is exactly 462,193,248 bytes (0.43 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is neutts-air'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.

neuphonic · audio tts

neutts-air

neuphonic/neutts-air

neutts-air at Q4_K_M is exactly 462,193,248 bytes (0.43 GiB / 0.46 GB) — an effective 4.944 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

748M

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_K_M	0.43 GiB	462,193,248	4.944	—	abliter8-ai
Q4_K_M	0.43 GiB	462,193,344	4.944	—	abliter8-ai
Q4_0	0.49 GiB	527,054,304	5.638	—	neuphonic
Q8_0	0.55 GiB	595,453,536	6.369	—	abliter8-ai
Q8_0	0.55 GiB	595,453,632	6.369	—	abliter8-ai
Q8_0	0.75 GiB	802,658,528	8.585	—	neuphonic

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 Ace-Step1.5 vs Qwen3-TTS-12Hz-0.6B-Base vs OmniVoice vs orpheus-3b-0.1-ft vs VieNeu-TTS-0.3B 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_M at roughly 0.39 GiB. The real file is 0.43 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

32768

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

false

This model declares a sliding window but sets use_sliding_window: false, so the window is not applied. Honouring the field without the flag understates KV for the whole family.

Questions people ask

How much VRAM does neutts-air need?: Q4_K_M is exactly 462,193,248 bytes (0.43 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is neutts-air'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 neutts-air 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.