openai/clip-vit-base-patch32
openai/clip-vit-base-patch32
Parameters
148M
Context
77
Downloads
20.8M
Likes
1K
Architecture
clip
12 layers · head 64 · hidden 512
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 2.8 GB RAM 32.0 · Disk 39.4 | 4.8 GB RAM 32.0 · Disk 65.4 | 19.0 GB RAM 32.0 · Disk 104.4 |
| FP88bit | 2.6 GB RAM 32.0 · Disk 39.2 | 4.6 GB RAM 32.0 · Disk 65.2 | 18.8 GB RAM 32.0 · Disk 104.2 |
| INT88bit | 2.6 GB RAM 32.0 · Disk 39.2 | 4.6 GB RAM 32.0 · Disk 65.2 | 18.8 GB RAM 32.0 · Disk 104.2 |
| AWQ4bit | 2.5 GB RAM 32.0 · Disk 39.1 | 4.6 GB RAM 32.0 · Disk 65.1 | 18.7 GB RAM 32.0 · Disk 104.1 |
| GPTQ4bit | 2.5 GB RAM 32.0 · Disk 39.1 | 4.6 GB RAM 32.0 · Disk 65.1 | 18.7 GB RAM 32.0 · Disk 104.1 |
| GGUF4bit | 2.5 GB RAM 32.0 · Disk 39.1 | 4.6 GB RAM 32.0 · Disk 65.1 | 18.7 GB RAM 32.0 · Disk 104.1 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 13714.3 tok/s
Effective production throughput ≈ 9600 tok/s
score 0.5708
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5656
8× H200 SXM
1128 GB VRAM
≈ 219428.6 tok/s
Effective production throughput ≈ 153600 tok/s
score 0.2197
1× RTX 5060 Ti
8 GB VRAM
≈ 6400 tok/s
Effective production throughput ≈ 4480 tok/s
score 0.644
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$9.9
/mo · vast
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
$58.7
/mo · vast