intfloat/multilingual-e5-large
intfloat/multilingual-e5-large
Microsoft E5 multilingual embedding.
Parameters
558M
Context
514
Downloads
6.6M
Likes
1.3K
Architecture
xlm-roberta
24 layers · head 64 · hidden 1024
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 2.7 GB RAM 32.0 · Disk 40.6 | 2.9 GB RAM 32.0 · Disk 66.6 | 3.3 GB RAM 32.0 · Disk 105.6 |
| FP88bit | 2.0 GB RAM 32.0 · Disk 39.8 | 2.2 GB RAM 32.0 · Disk 65.8 | 2.5 GB RAM 32.0 · Disk 104.8 |
| INT88bit | 2.0 GB RAM 32.0 · Disk 39.8 | 2.2 GB RAM 32.0 · Disk 65.8 | 2.5 GB RAM 32.0 · Disk 104.8 |
| AWQ4bit | 1.6 GB RAM 32.0 · Disk 39.4 | 1.8 GB RAM 32.0 · Disk 65.4 | 2.1 GB RAM 32.0 · Disk 104.4 |
| GPTQ4bit | 1.6 GB RAM 32.0 · Disk 39.4 | 1.8 GB RAM 32.0 · Disk 65.4 | 2.1 GB RAM 32.0 · Disk 104.4 |
| GGUF4bit | 1.6 GB RAM 32.0 · Disk 39.4 | 1.8 GB RAM 32.0 · Disk 65.4 | 2.1 GB RAM 32.0 · Disk 104.4 |
GPU Recommendations
1× RTX 3080
10 GB VRAM
≈ 5630 vec/s
Effective production throughput ≈ 4504 vectors/s
score 0.5416
1× RTX 4060 Ti
8 GB VRAM
≈ 2133 vec/s
Effective production throughput ≈ 1706.4 vectors/s
score 0.5504
8× RTX 3080
80 GB VRAM
≈ 45037 vec/s
Effective production throughput ≈ 36029.6 vectors/s
score 0.3667
2× RTX 3080
20 GB VRAM
≈ 11259 vec/s
Effective production throughput ≈ 9007.2 vectors/s
score 0.4535
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$35.7
/mo · vast
RTX 4060 Ti
8 GB VRAM
$49.6
/mo · vast
RTX 3080
10 GB VRAM
$64.3
/mo · vast
RTX 4070S Ti
16 GB VRAM
$68.5
/mo · vast
L4
24 GB VRAM
$76.2
/mo · vast