FacebookAI/xlm-roberta-large
FacebookAI/xlm-roberta-large
Parameters
558M
Context
514
Downloads
6.4M
Likes
525
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 | 4.1 GB RAM 32.0 · Disk 40.6 | 8.9 GB RAM 32.0 · Disk 66.6 | 39.8 GB RAM 59.8 · Disk 105.6 |
| FP88bit | 3.5 GB RAM 32.0 · Disk 39.8 | 8.2 GB RAM 32.0 · Disk 65.8 | 39.1 GB RAM 58.7 · Disk 104.8 |
| INT88bit | 3.5 GB RAM 32.0 · Disk 39.8 | 8.2 GB RAM 32.0 · Disk 65.8 | 39.1 GB RAM 58.7 · Disk 104.8 |
| AWQ4bit | 3.2 GB RAM 32.0 · Disk 39.4 | 7.8 GB RAM 32.0 · Disk 65.4 | 38.8 GB RAM 58.2 · Disk 104.4 |
| GPTQ4bit | 3.2 GB RAM 32.0 · Disk 39.4 | 7.8 GB RAM 32.0 · Disk 65.4 | 38.8 GB RAM 58.2 · Disk 104.4 |
| GGUF4bit | 3.2 GB RAM 32.0 · Disk 39.4 | 7.8 GB RAM 32.0 · Disk 65.4 | 38.8 GB RAM 58.2 · Disk 104.4 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 3555.6 tok/s
Effective production throughput ≈ 2488.9 tok/s
score 0.6255
1× RTX 5060 Ti
8 GB VRAM
≈ 1659.3 tok/s
Effective production throughput ≈ 1161.5 tok/s
score 0.639
8× H200 SXM
1128 GB VRAM
≈ 56888.9 tok/s
Effective production throughput ≈ 39822.2 tok/s
score 0.2197
1× RTX 5070
12 GB VRAM
≈ 2488.9 tok/s
Effective production throughput ≈ 1742.2 tok/s
score 0.6677
💬 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