answerdotai/ModernBERT-base
answerdotai/ModernBERT-base
Parameters
194.4M
Context
8K
Downloads
5.5M
Likes
1.1K
Architecture
modernbert
22 layers · head 64 · hidden 768
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 3.1 GB RAM 32.0 · Disk 39.6 | 7.1 GB RAM 32.0 · Disk 65.6 | 34.3 GB RAM 51.4 · Disk 104.6 |
| FP88bit | 2.9 GB RAM 32.0 · Disk 39.3 | 6.9 GB RAM 32.0 · Disk 65.3 | 34.0 GB RAM 51.0 · Disk 104.3 |
| INT88bit | 2.9 GB RAM 32.0 · Disk 39.3 | 6.9 GB RAM 32.0 · Disk 65.3 | 34.0 GB RAM 51.0 · Disk 104.3 |
| AWQ4bit | 2.8 GB RAM 32.0 · Disk 39.2 | 6.8 GB RAM 32.0 · Disk 65.2 | 33.9 GB RAM 50.8 · Disk 104.2 |
| GPTQ4bit | 2.8 GB RAM 32.0 · Disk 39.2 | 6.8 GB RAM 32.0 · Disk 65.2 | 33.9 GB RAM 50.8 · Disk 104.2 |
| GGUF4bit | 2.8 GB RAM 32.0 · Disk 39.2 | 6.8 GB RAM 32.0 · Disk 65.2 | 33.9 GB RAM 50.8 · Disk 104.2 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 10666.7 tok/s
Effective production throughput ≈ 7466.7 tok/s
score 0.6078
1× RTX 5060 Ti
8 GB VRAM
≈ 4977.8 tok/s
Effective production throughput ≈ 3484.5 tok/s
score 0.6667
8× H200 SXM
1128 GB VRAM
≈ 170666.7 tok/s
Effective production throughput ≈ 119466.7 tok/s
score 0.2197
1× RTX 5070
12 GB VRAM
≈ 7466.7 tok/s
Effective production throughput ≈ 5226.7 tok/s
score 0.6441
💬 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