google/vit-base-patch16-224
google/vit-base-patch16-224
Parameters
109.5M
Context
—
Downloads
8.8M
Likes
1K
Architecture
vit
12 layers · head 64 · hidden 768
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 2.6 GB RAM 32.0 · Disk 39.3 | 3.0 GB RAM 32.0 · Disk 65.3 | 5.2 GB RAM 32.0 · Disk 104.3 |
| FP88bit | 2.5 GB RAM 32.0 · Disk 39.2 | 2.8 GB RAM 32.0 · Disk 65.2 | 5.0 GB RAM 32.0 · Disk 104.2 |
| INT88bit | 2.5 GB RAM 32.0 · Disk 39.2 | 2.8 GB RAM 32.0 · Disk 65.2 | 5.0 GB RAM 32.0 · Disk 104.2 |
| AWQ4bit | 2.4 GB RAM 32.0 · Disk 39.1 | 2.8 GB RAM 32.0 · Disk 65.1 | 5.0 GB RAM 32.0 · Disk 104.1 |
| GPTQ4bit | 2.4 GB RAM 32.0 · Disk 39.1 | 2.8 GB RAM 32.0 · Disk 65.1 | 5.0 GB RAM 32.0 · Disk 104.1 |
| GGUF4bit | 2.4 GB RAM 32.0 · Disk 39.1 | 2.8 GB RAM 32.0 · Disk 65.1 | 5.0 GB RAM 32.0 · Disk 104.1 |
GPU Recommendations
1× RTX 3080 Ti
12 GB VRAM
≈ 18240 tok/s
Effective production throughput ≈ 12768 tok/s
score 0.556
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5349
8× RTX 5080
128 GB VRAM
≈ 61440 tok/s
Effective production throughput ≈ 43008 tok/s
score 0.3573
1× RTX 3080
10 GB VRAM
≈ 15200 tok/s
Effective production throughput ≈ 10640 tok/s
score 0.5673
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$44.3
/mo · vast
RTX 3080
10 GB VRAM
$69.2
/mo · vast
RTX 4060 Ti
8 GB VRAM
$71.4
/mo · vast
RTX 3080 Ti
12 GB VRAM
$79.5
/mo · vast
RTX 3090
24 GB VRAM
$88.4
/mo · vast