sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Parameters
117.2M
Context
512
Downloads
46.3M
Likes
1.4K
Architecture
bert
12 layers · head 32 · hidden 384
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 1.5 GB RAM 32.0 · Disk 39.3 | 1.7 GB RAM 32.0 · Disk 65.3 | 2.0 GB RAM 32.0 · Disk 104.3 |
| FP88bit | 1.4 GB RAM 32.0 · Disk 39.2 | 1.5 GB RAM 32.0 · Disk 65.2 | 1.9 GB RAM 32.0 · Disk 104.2 |
| INT88bit | 1.4 GB RAM 32.0 · Disk 39.2 | 1.5 GB RAM 32.0 · Disk 65.2 | 1.9 GB RAM 32.0 · Disk 104.2 |
| AWQ4bit | 1.3 GB RAM 32.0 · Disk 39.1 | 1.5 GB RAM 32.0 · Disk 65.1 | 1.8 GB RAM 32.0 · Disk 104.1 |
| GPTQ4bit | 1.3 GB RAM 32.0 · Disk 39.1 | 1.5 GB RAM 32.0 · Disk 65.1 | 1.8 GB RAM 32.0 · Disk 104.1 |
| GGUF4bit | 1.3 GB RAM 32.0 · Disk 39.1 | 1.5 GB RAM 32.0 · Disk 65.1 | 1.8 GB RAM 32.0 · Disk 104.1 |
GPU Recommendations
1× RTX 5060 Ti
8 GB VRAM
≈ 14933 vec/s
Effective production throughput ≈ 11946.4 vectors/s
score 0.5392
1× RTX 4060 Ti
8 GB VRAM
≈ 9600 vec/s
Effective production throughput ≈ 7680 vectors/s
score 0.5391
8× RTX 5060 Ti
64 GB VRAM
≈ 119467 vec/s
Effective production throughput ≈ 95573.6 vectors/s
score 0.3487
2× RTX 4060 Ti
16 GB VRAM
≈ 19200 vec/s
Effective production throughput ≈ 15360 vectors/s
score 0.4475
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3080
10 GB VRAM
$58.6
/mo · vast
Tesla V100
16 GB VRAM
$64.8
/mo · vast
RTX 4070S Ti
16 GB VRAM
$68.5
/mo · vast
RTX 4060 Ti
8 GB VRAM
$78.9
/mo · vast
RTX 3080 Ti
12 GB VRAM
$79.5
/mo · vast