How much VRAM does tada-3b-ml need?

Q8_0 is exactly 5,579,404,608 bytes (5.20 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is tada-3b-ml's KV cache?

3.50 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.

HumeAI · audio tts

tada-3b-ml

HumeAI/tada-3b-ml

tada-3b-ml at Q8_0 is exactly 5,579,404,608 bytes (5.20 GiB / 5.58 GB) — an effective 10.563 bits per weight, not the nominal 8. Its KV cache at 32K is 3.50 GiB.

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

Parameters

4.2B

Architecture

wav2vec2

28 layers

Context

131,072

native (config.json)

License

llama3.2

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q8_0	5.20 GiB	5,579,404,608	10.563	—	cstr
Q4_K	5.77 GiB	6,195,967,296	11.730	—	cstr
F163 shards	8.06 GiB	8,658,770,720	16.392	—	cstr

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.44 GiB	0.44 GiB	—	28 / 0 / 0
8,192	0.88 GiB	0.88 GiB	—	28 / 0 / 0
16,384	1.75 GiB	1.75 GiB	—	28 / 0 / 0
32,768	3.50 GiB	3.50 GiB	—	28 / 0 / 0
65,536	7.00 GiB	7.00 GiB	—	28 / 0 / 0
131,072	14.00 GiB	14.00 GiB	—	28 / 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 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 Q8_0 at roughly 2.21 GiB. The real file is 5.20 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

128

Hidden size

3072

Vocab

128,256

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does tada-3b-ml need?: Q8_0 is exactly 5,579,404,608 bytes (5.20 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is tada-3b-ml's KV cache?: 3.50 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 tada-3b-ml 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.