TranslationGoogle-t5

google-t5/t5-base

google-t5/t5-base

Parameters

222.9M

Context

—

Downloads

4.1M

Likes

791

Architecture

t5

View on HuggingFace

GPU Requirements

VRAM / RAM / disk estimates by quantization and usage scenario

QuantizationMinimumRecommendedProduction
FP1616bit
5.5 GB
RAM 32.0 · Disk 39.7
21.3 GB
RAM 32.0 · Disk 65.7
118.2 GB
RAM 177.3 · Disk 104.7
FP88bit
5.2 GB
RAM 32.0 · Disk 39.3
21.0 GB
RAM 32.0 · Disk 65.3
117.9 GB
RAM 176.8 · Disk 104.3
INT88bit
5.2 GB
RAM 32.0 · Disk 39.3
21.0 GB
RAM 32.0 · Disk 65.3
117.9 GB
RAM 176.8 · Disk 104.3
AWQ4bit
5.1 GB
RAM 32.0 · Disk 39.2
20.8 GB
RAM 32.0 · Disk 65.2
117.8 GB
RAM 176.6 · Disk 104.2
GPTQ4bit
5.1 GB
RAM 32.0 · Disk 39.2
20.8 GB
RAM 32.0 · Disk 65.2
117.8 GB
RAM 176.6 · Disk 104.2
GGUF4bit
5.1 GB
RAM 32.0 · Disk 39.2
20.9 GB
RAM 32.0 · Disk 65.2
117.8 GB
RAM 176.6 · Disk 104.2

GPU Recommendations

Best ValueBEST

1× RTX 5090

32 GB VRAM

$155/mo

≈ 16290.9 tok/s

Effective production throughput ≈ 11403.6 tok/s

score 0.6732

Deploy on vast ↗
Cheapest

2× Tesla V100

32 GB VRAM

$71.4/mo

≈ 0 tok/s (N/A — benchmark unavailable)

Effective production throughput ≈ 0 tok/s

score 0.6197

Deploy on vast ↗
Performance

8× H200 SXM

1128 GB VRAM

$20,440/mo

≈ 139636.4 tok/s

Effective production throughput ≈ 97745.5 tok/s

score 0.2197

Min Complexity

1× L4

24 GB VRAM

$76.2/mo

≈ 2727.3 tok/s

Effective production throughput ≈ 1909.1 tok/s

score 0.659

Deploy on vast ↗

💬 Community — real deployment experience

0 Articles · 0 Benchmarks

View Community →

GPUs that fit (single card)

L4

24 GB VRAM

$76.2

/mo · vast

RTX 3090

24 GB VRAM

$79.6

/mo · vast

RTX 5090

32 GB VRAM

$155

/mo · vast

A10

24 GB VRAM

$177

/mo · vast

RTX 4090

24 GB VRAM

$190

/mo · tensordock

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