google-t5/t5-small
google-t5/t5-small
Parameters
60.5M
Context
—
Downloads
22.8M
Likes
592
Architecture
t5
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 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 |
| FP88bit | 5.0 GB RAM 32.0 · Disk 39.1 | 20.8 GB RAM 32.0 · Disk 65.1 | 117.7 GB RAM 176.5 · Disk 104.1 |
| INT88bit | 5.0 GB RAM 32.0 · Disk 39.1 | 20.8 GB RAM 32.0 · Disk 65.1 | 117.7 GB RAM 176.5 · Disk 104.1 |
| AWQ4bit | 5.0 GB RAM 32.0 · Disk 39.1 | 20.7 GB RAM 32.0 · Disk 65.1 | 117.6 GB RAM 176.5 · Disk 104.1 |
| GPTQ4bit | 5.0 GB RAM 32.0 · Disk 39.1 | 20.7 GB RAM 32.0 · Disk 65.1 | 117.6 GB RAM 176.5 · Disk 104.1 |
| GGUF4bit | 5.0 GB RAM 32.0 · Disk 39.1 | 20.7 GB RAM 32.0 · Disk 65.1 | 117.6 GB RAM 176.5 · Disk 104.1 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 59733.3 tok/s
Effective production throughput ≈ 41813.3 tok/s
score 0.6705
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6195
8× H200 SXM
1128 GB VRAM
≈ 512000 tok/s
Effective production throughput ≈ 358400 tok/s
score 0.2197
1× RTX 3090
24 GB VRAM
≈ 31200 tok/s
Effective production throughput ≈ 21840 tok/s
score 0.6646
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3090
24 GB VRAM
$78.7
/mo · vast
RTX 4090D
24 GB VRAM
$117
/mo · vast
A10
24 GB VRAM
$147
/mo · vast
L4
24 GB VRAM
$148
/mo · vast
RTX 4090
24 GB VRAM
$190
/mo · tensordock