AudioHexgrad

hexgrad/Kokoro-82M

hexgrad/Kokoro-82M

Parameters

82M

Context

Downloads

12M

Likes

6.7K

Architecture

View on HuggingFace

GPU Requirements

VRAM / RAM / disk estimates by quantization and usage scenario

QuantizationMinimumRecommendedProduction
FP1616bit
3.5 GB
RAM 32.0 · Disk 39.2
4.5 GB
RAM 32.0 · Disk 65.2
6.6 GB
RAM 32.0 · Disk 104.2
FP88bit
3.3 GB
RAM 32.0 · Disk 39.1
4.3 GB
RAM 32.0 · Disk 65.1
6.4 GB
RAM 32.0 · Disk 104.1
INT88bit
3.3 GB
RAM 32.0 · Disk 39.1
4.3 GB
RAM 32.0 · Disk 65.1
6.4 GB
RAM 32.0 · Disk 104.1
AWQ4bit
3.2 GB
RAM 32.0 · Disk 39.1
4.2 GB
RAM 32.0 · Disk 65.1
6.3 GB
RAM 32.0 · Disk 104.1
GPTQ4bit
3.2 GB
RAM 32.0 · Disk 39.1
4.2 GB
RAM 32.0 · Disk 65.1
6.4 GB
RAM 32.0 · Disk 104.1
GGUF4bit
3.2 GB
RAM 32.0 · Disk 39.1
4.2 GB
RAM 32.0 · Disk 65.1
6.4 GB
RAM 32.0 · Disk 104.1

GPU Recommendations

Best ValueBEST

1× RTX 5080

16 GB VRAM

$90.6/mo

≈ 22600 chars/s

Effective production throughput ≈ 15820 chars/s

score 0.5656

Deploy on vast ↗
Cheapest

1× RTX 5060 Ti

8 GB VRAM

$39.7/mo

≈ 4800 chars/s

Effective production throughput ≈ 3360 chars/s

score 0.6337

Deploy on vast ↗
Performance

8× RTX 4090

192 GB VRAM

$792/mo

≈ 264000 chars/s

Effective production throughput ≈ 184800 chars/s

score 0.3665

Deploy on vast ↗
Min Complexity

1× RTX 5070

12 GB VRAM

$75.2/mo

≈ 12200 chars/s

Effective production throughput ≈ 8540 chars/s

score 0.5875

Deploy on vast ↗

💬 Community — real deployment experience

0 Articles · 0 Benchmarks

View Community →

GPUs that fit (single card)

RTX 5060 Ti

8 GB VRAM

$39.7

/mo · vast

RTX 4070S Ti

16 GB VRAM

$49.5

/mo · vast

RTX 4080S

16 GB VRAM

$50.0

/mo · vast

RTX 5070

12 GB VRAM

$75.2

/mo · vast

RTX 3090

24 GB VRAM

$76.5

/mo · vast

AmciHub

AI Model Deployment & Compute Intelligence — analyze AI model requirements, GPU performance, cloud pricing and deployment costs to find the right deployment solution.

© 2026 AmciHub. All rights reserved. Model → Requirement → GPU → Benchmark → Cloud → Cost → Recommendation