cross-encoder/ms-marco-MiniLM-L4-v2
cross-encoder/ms-marco-MiniLM-L4-v2
Parameters
18.8M
Context
512
Downloads
9M
Likes
28
Architecture
bert
4 layers · head 32 · hidden 384
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 2.3 GB RAM 32.0 · Disk 39.1 | 2.7 GB RAM 32.0 · Disk 65.1 | 5.3 GB RAM 32.0 · Disk 104.1 |
| FP88bit | 2.3 GB RAM 32.0 · Disk 39.0 | 2.7 GB RAM 32.0 · Disk 65.0 | 5.3 GB RAM 32.0 · Disk 104.0 |
| INT88bit | 2.3 GB RAM 32.0 · Disk 39.0 | 2.7 GB RAM 32.0 · Disk 65.0 | 5.3 GB RAM 32.0 · Disk 104.0 |
| AWQ4bit | 2.3 GB RAM 32.0 · Disk 39.0 | 2.7 GB RAM 32.0 · Disk 65.0 | 5.3 GB RAM 32.0 · Disk 104.0 |
| GPTQ4bit | 2.3 GB RAM 32.0 · Disk 39.0 | 2.7 GB RAM 32.0 · Disk 65.0 | 5.3 GB RAM 32.0 · Disk 104.0 |
| GGUF4bit | 2.3 GB RAM 32.0 · Disk 39.0 | 2.7 GB RAM 32.0 · Disk 65.0 | 5.3 GB RAM 32.0 · Disk 104.0 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 96000 tok/s
Effective production throughput ≈ 67200 tok/s
score 0.5401
1× RTX 5060 Ti
8 GB VRAM
≈ 44800 tok/s
Effective production throughput ≈ 31360 tok/s
score 0.5827
8× H200 SXM
1128 GB VRAM
≈ 1536000 tok/s
Effective production throughput ≈ 1075200 tok/s
score 0.2197
1× RTX 5070
12 GB VRAM
≈ 67200 tok/s
Effective production throughput ≈ 47040 tok/s
score 0.5539
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
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
$54.1
/mo · vast
RTX 5070 Ti
16 GB VRAM
$83.1
/mo · vast