Sora-2
openai/Sora-2
OpenAI Sora-2 open weights video model.
Parameters
8B
Context
16K
Downloads
190K
Likes
900
Architecture
sora
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 35.0 GB RAM 52.5 · Disk 62.3 | 40.1 GB RAM 60.1 · Disk 88.3 | 49.0 GB RAM 73.5 · Disk 127.3 |
| FP88bit | 20.3 GB RAM 32.0 · Disk 50.6 | 24.6 GB RAM 36.9 · Disk 76.6 | 32.9 GB RAM 49.3 · Disk 115.6 |
| INT88bit | 20.3 GB RAM 32.0 · Disk 50.6 | 24.6 GB RAM 36.9 · Disk 76.6 | 32.9 GB RAM 49.3 · Disk 115.6 |
| AWQ4bit | 13.2 GB RAM 32.0 · Disk 45.0 | 17.2 GB RAM 32.0 · Disk 71.0 | 25.2 GB RAM 37.7 · Disk 110.0 |
| GPTQ4bit | 13.2 GB RAM 32.0 · Disk 45.1 | 17.3 GB RAM 32.0 · Disk 71.1 | 25.3 GB RAM 37.9 · Disk 110.1 |
| GGUF4bit | 13.4 GB RAM 32.0 · Disk 45.3 | 17.5 GB RAM 32.0 · Disk 71.3 | 25.5 GB RAM 38.2 · Disk 110.3 |
GPU Recommendations
1× RTX 5090
32 GB VRAM
≈ 288 video-sec/GPU-h
Effective production throughput ≈ 172.8 video-sec/GPU-h
score 0.6408
1× RTX 3090
24 GB VRAM
≈ 288 video-sec/GPU-h
Effective production throughput ≈ 172.8 video-sec/GPU-h
score 0.6862
8× H100 SXM
640 GB VRAM
≈ 288 video-sec/GPU-h
Effective production throughput ≈ 172.8 video-sec/GPU-h
score 0.2415
1× RTX 4090
24 GB VRAM
≈ 288 video-sec/GPU-h
Effective production throughput ≈ 172.8 video-sec/GPU-h
score 0.6862
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
RTX 3090
24 GB VRAM
$76.5
/mo · vast
RTX 4090
24 GB VRAM
$99.0
/mo · vast
RTX 4090D
24 GB VRAM
$117
/mo · vast
L4
24 GB VRAM
$147
/mo · vast
A10
24 GB VRAM
$176
/mo · vast