sentence-transformers/all-MiniLM-L6-v2
sentence-transformers/all-MiniLM-L6-v2
Parameters
22.3M
Context
512
Downloads
244M
Likes
6.1K
Architecture
bert
6 layers · head 32 · hidden 384
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 1.3 GB RAM 32.0 · Disk 39.1 | 1.4 GB RAM 32.0 · Disk 65.1 | 1.7 GB RAM 32.0 · Disk 104.1 |
| FP88bit | 1.2 GB RAM 32.0 · Disk 39.0 | 1.4 GB RAM 32.0 · Disk 65.0 | 1.7 GB RAM 32.0 · Disk 104.0 |
| INT88bit | 1.2 GB RAM 32.0 · Disk 39.0 | 1.4 GB RAM 32.0 · Disk 65.0 | 1.7 GB RAM 32.0 · Disk 104.0 |
| AWQ4bit | 1.2 GB RAM 32.0 · Disk 39.0 | 1.4 GB RAM 32.0 · Disk 65.0 | 1.7 GB RAM 32.0 · Disk 104.0 |
| GPTQ4bit | 1.2 GB RAM 32.0 · Disk 39.0 | 1.4 GB RAM 32.0 · Disk 65.0 | 1.7 GB RAM 32.0 · Disk 104.0 |
| GGUF4bit | 1.2 GB RAM 32.0 · Disk 39.0 | 1.4 GB RAM 32.0 · Disk 65.0 | 1.7 GB RAM 32.0 · Disk 104.0 |
GPU Recommendations
1× RTX 5060 Ti
8 GB VRAM
≈ 89600 vec/s
Effective production throughput ≈ 71680 vectors/s
score 0.5379
1× RTX 4060 Ti
8 GB VRAM
≈ 57600 vec/s
Effective production throughput ≈ 46080 vectors/s
score 0.5373
8× RTX 5060 Ti
64 GB VRAM
≈ 716800 vec/s
Effective production throughput ≈ 573440 vectors/s
score 0.3548
2× RTX 4060 Ti
16 GB VRAM
≈ 115200 vec/s
Effective production throughput ≈ 92160 vectors/s
score 0.4479
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$39.5
/mo · vast
RTX 3080
10 GB VRAM
$58.6
/mo · vast
RTX 4060 Ti
8 GB VRAM
$68.8
/mo · vast
L4
24 GB VRAM
$78.7
/mo · vast
RTX 3080 Ti
12 GB VRAM
$79.5
/mo · vast