faster-whisper-large-v3
Systran/faster-whisper-large-v3
CTranslate2 optimized Whisper, 4x faster inference.
Parameters
1.5B
Context
448
Downloads
2.2M
Likes
2.9K
Architecture
whisper
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 9.5 GB RAM 32.0 · Disk 43.4 | 10.5 GB RAM 32.0 · Disk 69.4 | 12.2 GB RAM 32.0 · Disk 108.4 |
| FP88bit | 6.1 GB RAM 32.0 · Disk 41.2 | 7.0 GB RAM 32.0 · Disk 67.2 | 8.5 GB RAM 32.0 · Disk 106.2 |
| INT88bit | 6.1 GB RAM 32.0 · Disk 41.2 | 7.0 GB RAM 32.0 · Disk 67.2 | 8.5 GB RAM 32.0 · Disk 106.2 |
| AWQ4bit | 4.5 GB RAM 32.0 · Disk 40.1 | 5.3 GB RAM 32.0 · Disk 66.1 | 6.7 GB RAM 32.0 · Disk 105.1 |
| GPTQ4bit | 4.5 GB RAM 32.0 · Disk 40.1 | 5.3 GB RAM 32.0 · Disk 66.1 | 6.7 GB RAM 32.0 · Disk 105.1 |
| GGUF4bit | 4.6 GB RAM 32.0 · Disk 40.2 | 5.4 GB RAM 32.0 · Disk 66.2 | 6.8 GB RAM 32.0 · Disk 105.2 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ RTF 0.37
Effective production throughput ≈ 0.3 RTF
score 0.583
1× RTX 5060 Ti
8 GB VRAM
≈ RTF 0.79
Effective production throughput ≈ 0.6 RTF
score 0.6684
8× RTX 4090
192 GB VRAM
≈ RTF 0.11
Effective production throughput ≈ 0.1 RTF
score 0.3665
1× RTX 5070
12 GB VRAM
≈ RTF 0.52
Effective production throughput ≈ 0.4 RTF
score 0.6106
💬 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
$75.2
/mo · vast
RTX 3090
24 GB VRAM
$76.5
/mo · vast