Skip to content
Updated minutes ago
HuggingFace

Kokoro TTS 82M

Hexagrad · dense · 0.082B parameters · 2,048 context

Quality
50.0

Parameters

0.082B

Context Window

2K tokens

Architecture

Dense

Best GPU

B200 SXM

Intelligence Brief

Kokoro TTS 82M is a 0.082B parameter DENSE model from Hexagrad, featuring Multi-Head Attention (MHA) with 6 layers and 512 hidden dimensions. With a 2,048 token context window, it supports general text generation. For self-hosted inference, B200 SXM delivers optimal throughput at $4261/month.

Architecture Details

TypeDENSE
Total Parameters0.082B
Active Parameters0.082B
Layers6
Hidden Dimension512
Attention Heads8
KV Heads8
Head Dimension64
Vocab Size32,000

Memory Requirements

BF16 Weights

0.2 GB

FP8 Weights

0.1 GB

INT4 Weights

0.0 GB

KV-Cache per Token6144 bytes
Activation Estimate0.01 GB

GPU Compatibility Matrix

Kokoro TTS 82M is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
B300288GB
B100 SXM192GB
GB200 NVL72 (per GPU)192GB
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
H200 SXM141GB
GH20096GB
Ada Lovelace(11 GPUs)
L40S48GB
RTX 6000 Ada48GB
Ampere(16 GPUs)
A100 80GB SXM80GB
A100 80GB PCIe80GB
RTX A600048GB
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

B200 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

83/100

score

Throughput

3.5K tok/s

Latency (ITL)

0.3ms

Est. TTFT

0ms

Cost/Month

$4261

Cost/M Tokens

$0.46

Use this config →
B100 SXMoptimal

FP8 · 1 GPU · tensorrt-llm

83/100

score

Throughput

3.5K tok/s

Latency (ITL)

0.3ms

Est. TTFT

0ms

Cost/Month

$4271

Cost/M Tokens

$0.46

Use this config →
GB200 NVL72 (per GPU)optimal

FP8 · 1 GPU · tensorrt-llm

83/100

score

Throughput

3.5K tok/s

Latency (ITL)

0.3ms

Est. TTFT

0ms

Cost/Month

$6169

Cost/M Tokens

$0.67

Use this config →

Deployment Options

API

API Deployment

No API pricing available

Self-Hosted

Single GPU

B200 SXM

$4261/mo

Min VRAM: 0 GB

Scale

Multi-GPU

B200 SXM

3.5K tok/s

Best available config

API Pricing Comparison

No API pricing data available for this model.

Performance Estimates

Throughput by GPU

B200 SXM
3.5K tok/s
B100 SXM
3.5K tok/s
GB200 NVL72 (per GPU)
3.5K tok/s

VRAM Breakdown (B200 SXM, FP8)

Weights
KV
Act
Weights 0.1 GBKV-Cache 0.1 GBActivations 0.1 GBOverhead 0.0 GB

Precision Impact

bf16

0.2 GB

weights/GPU

fp8

0.1 GB

weights/GPU

~3.5K tok/s

int4

0.0 GB

weights/GPU

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

ollama

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Kokoro TTS 82M

Similar Models

Smaller context, Smaller modelCompare →
Larger context, Larger modelCompare →

Frequently Asked Questions

How much VRAM does Kokoro TTS 82M need for inference?

Kokoro TTS 82M requires approximately 0.2 GB of VRAM at BF16 precision, 0.1 GB at FP8, or 0.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (6144 bytes per token) and activations (~0.01 GB).

What is the best GPU for Kokoro TTS 82M?

The top recommended GPU for Kokoro TTS 82M is the B200 SXM using FP8 precision. It achieves approximately 3.5K tokens/sec at an estimated cost of $4261/month ($0.46/M tokens). Score: 83/100.

How much does Kokoro TTS 82M inference cost?

Kokoro TTS 82M inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.