google-bert/bert-base-uncased
google-bert/bert-base-uncased
Parameters
108.4M
Context
512
Downloads
115.9M
Likes
2.7K
Architecture
bert
12 layers · head 64 · hidden 768
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 2.7 GB RAM 32.0 · Disk 39.3 | 4.9 GB RAM 32.0 · Disk 65.3 | 19.8 GB RAM 32.0 · Disk 104.3 |
| FP88bit | 2.6 GB RAM 32.0 · Disk 39.2 | 4.8 GB RAM 32.0 · Disk 65.2 | 19.6 GB RAM 32.0 · Disk 104.2 |
| INT88bit | 2.6 GB RAM 32.0 · Disk 39.2 | 4.8 GB RAM 32.0 · Disk 65.2 | 19.6 GB RAM 32.0 · Disk 104.2 |
| AWQ4bit | 2.5 GB RAM 32.0 · Disk 39.1 | 4.7 GB RAM 32.0 · Disk 65.1 | 19.6 GB RAM 32.0 · Disk 104.1 |
| GPTQ4bit | 2.5 GB RAM 32.0 · Disk 39.1 | 4.7 GB RAM 32.0 · Disk 65.1 | 19.6 GB RAM 32.0 · Disk 104.1 |
| GGUF4bit | 2.5 GB RAM 32.0 · Disk 39.1 | 4.7 GB RAM 32.0 · Disk 65.1 | 19.6 GB RAM 32.0 · Disk 104.1 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 19200 tok/s
Effective production throughput ≈ 13440 tok/s
score 0.574
1× Tesla V100
16 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.5686
8× H200 SXM
1128 GB VRAM
≈ 307200 tok/s
Effective production throughput ≈ 215040 tok/s
score 0.2197
1× RTX 5060 Ti
8 GB VRAM
≈ 8960 tok/s
Effective production throughput ≈ 6272 tok/s
score 0.6504
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$20.3
/mo · vast
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
$58.7
/mo · vast