openai/clip-vit-large-patch14
openai/clip-vit-large-patch14
Parameters
424.9M
Context
77
Downloads
7.1M
Likes
2.1K
Architecture
clip
12 layers · head 64 · hidden 768
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 3.5 GB RAM 32.0 · Disk 40.2 | 5.7 GB RAM 32.0 · Disk 66.2 | 20.6 GB RAM 32.0 · Disk 105.2 |
| FP88bit | 3.0 GB RAM 32.0 · Disk 39.6 | 5.2 GB RAM 32.0 · Disk 65.6 | 20.1 GB RAM 32.0 · Disk 104.6 |
| INT88bit | 3.0 GB RAM 32.0 · Disk 39.6 | 5.2 GB RAM 32.0 · Disk 65.6 | 20.1 GB RAM 32.0 · Disk 104.6 |
| AWQ4bit | 2.7 GB RAM 32.0 · Disk 39.3 | 4.9 GB RAM 32.0 · Disk 65.3 | 19.8 GB RAM 32.0 · Disk 104.3 |
| GPTQ4bit | 2.7 GB RAM 32.0 · Disk 39.3 | 5.0 GB RAM 32.0 · Disk 65.3 | 19.8 GB RAM 32.0 · Disk 104.3 |
| GGUF4bit | 2.7 GB RAM 32.0 · Disk 39.3 | 5.0 GB RAM 32.0 · Disk 65.3 | 19.8 GB RAM 32.0 · Disk 104.3 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 4571.4 tok/s
Effective production throughput ≈ 3200 tok/s
score 0.5774
1× RTX 5060 Ti
8 GB VRAM
≈ 2133.3 tok/s
Effective production throughput ≈ 1493.3 tok/s
score 0.657
8× H200 SXM
1128 GB VRAM
≈ 73142.9 tok/s
Effective production throughput ≈ 51200 tok/s
score 0.2197
1× RTX 5070
12 GB VRAM
≈ 3200 tok/s
Effective production throughput ≈ 2240 tok/s
score 0.6035
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
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 5070
12 GB VRAM
$54.1
/mo · vast
Tesla V100
16 GB VRAM
$58.0
/mo · vast
RTX 4080S
16 GB VRAM
$64.6
/mo · vast