intfloat/multilingual-e5-base
intfloat/multilingual-e5-base
Parameters
276.9M
Context
514
Downloads
6.4M
Likes
410
Architecture
xlm-roberta
12 layers · head 64 · hidden 768
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 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 |
| FP88bit | 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 |
| INT88bit | 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 |
| AWQ4bit | 1.4 GB RAM 32.0 · Disk 39.2 | 1.6 GB RAM 32.0 · Disk 65.2 | 1.9 GB RAM 32.0 · Disk 104.2 |
| GPTQ4bit | 1.4 GB RAM 32.0 · Disk 39.2 | 1.6 GB RAM 32.0 · Disk 65.2 | 1.9 GB RAM 32.0 · Disk 104.2 |
| GGUF4bit | 1.4 GB RAM 32.0 · Disk 39.2 | 1.6 GB RAM 32.0 · Disk 65.2 | 1.9 GB RAM 32.0 · Disk 104.2 |
GPU Recommendations
1× RTX 5060 Ti
8 GB VRAM
≈ 6892 vec/s
Effective production throughput ≈ 5513.6 vectors/s
score 0.5444
1× RTX 4060 Ti
8 GB VRAM
≈ 4431 vec/s
Effective production throughput ≈ 3544.8 vectors/s
score 0.5435
8× RTX 5060 Ti
64 GB VRAM
≈ 55138 vec/s
Effective production throughput ≈ 44110.4 vectors/s
score 0.3588
2× RTX 4060 Ti
16 GB VRAM
≈ 8862 vec/s
Effective production throughput ≈ 7089.6 vectors/s
score 0.4483
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$39.7
/mo · vast
RTX 4060 Ti
8 GB VRAM
$59.2
/mo · vast
RTX 3080
10 GB VRAM
$64.3
/mo · vast
RTX 5060 Ti
8 GB VRAM
$68.8
/mo · vast
RTX 4070S Ti
16 GB VRAM
$68.9
/mo · vast