openai-community/gpt2
openai-community/gpt2
Parameters
137M
Context
—
Downloads
33.6M
Likes
3.9K
Architecture
gpt2
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 5.3 GB RAM 32.0 · Disk 39.4 | 21.0 GB RAM 32.0 · Disk 65.4 | 118.0 GB RAM 176.9 · Disk 104.4 |
| FP88bit | 5.1 GB RAM 32.0 · Disk 39.2 | 20.9 GB RAM 32.0 · Disk 65.2 | 117.8 GB RAM 176.7 · Disk 104.2 |
| INT88bit | 5.1 GB RAM 32.0 · Disk 39.2 | 20.9 GB RAM 32.0 · Disk 65.2 | 117.8 GB RAM 176.7 · Disk 104.2 |
| AWQ4bit | 5.0 GB RAM 32.0 · Disk 39.1 | 20.8 GB RAM 32.0 · Disk 65.1 | 117.7 GB RAM 176.5 · Disk 104.1 |
| GPTQ4bit | 5.0 GB RAM 32.0 · Disk 39.1 | 20.8 GB RAM 32.0 · Disk 65.1 | 117.7 GB RAM 176.5 · Disk 104.1 |
| GGUF4bit | 5.0 GB RAM 32.0 · Disk 39.1 | 20.8 GB RAM 32.0 · Disk 65.1 | 117.7 GB RAM 176.5 · Disk 104.1 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 25600 tok/s
Effective production throughput ≈ 17920 tok/s
score 0.6698
2× Tesla V100
32 GB VRAM
≈ 0 tok/s (N/A — benchmark unavailable)
Effective production throughput ≈ 0 tok/s
score 0.6193
8× H200 SXM
1128 GB VRAM
≈ 219428.6 tok/s
Effective production throughput ≈ 153600 tok/s
score 0.2197
1× L4
24 GB VRAM
≈ 4285.7 tok/s
Effective production throughput ≈ 3000 tok/s
score 0.6596
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
L4
24 GB VRAM
$76.2
/mo · vast
RTX 3090
24 GB VRAM
$88.4
/mo · vast
A10
24 GB VRAM
$176
/mo · vast
RTX 4090
24 GB VRAM
$190
/mo · tensordock
A100 SXM4
80 GB VRAM
$225
/mo · vast