Fourteen images per minute for under 40p per thousand. If that sounds too good to check, here are the actual numbers: we benchmarked Stable Diffusion 1.5 on the RTX 4060 across standard 512×512 generation workloads on a GigaGPU dedicated server.
Throughput Figures
| Metric | Value |
|---|---|
| Iterations/sec | 6.2 it/s |
| Seconds per image | 4.03 sec (25 steps) |
| Images per minute | 14.88 |
| Resolution | 512×512 |
| Sampler | Euler a / DPM++ 2M Karras |
| Performance rating | Excellent |
Benchmark conditions: 25-step generation at 512×512, batch size 1, FP16 precision. Using A1111 WebUI or ComfyUI backend.
VRAM Headroom
| Component | VRAM |
|---|---|
| Model weights | 3.2 GB |
| Sampling buffer | ~0.6 GB |
| Total RTX 4060 VRAM | 8 GB |
| Free headroom | ~4.8 GB |
With 4.8 GB free after loading, the 4060 can handle single LoRA adapters, moderate ControlNet workflows, and even 768×768 generation if you keep batch sizes at 1. It is not unlimited, but for SD 1.5’s modest appetite it provides genuine breathing room.
Cost Breakdown
| Cost Metric | Value |
|---|---|
| Server cost | £0.35/hr (£69/mo) |
| Cost per 1K images | £0.39 |
| Images per £1 | 2564 |
Under forty pence per thousand images makes the RTX 4060 one of the most cost-efficient SD 1.5 configurations we have tested. The Ada Lovelace architecture punches well above its price class here. Full cost comparisons at our benchmark dashboard.
Practical Takeaway
The RTX 4060 hits a genuine sweet spot for SD 1.5: fast enough for real-time previews during prompt engineering, cheap enough to leave running as a batch generation server. If you need to scale beyond 15 images per minute, the 4060 Ti pushes past 20 img/min with double the VRAM. For workflow planning, check our GPU selection guide.
Quick deploy:
docker run --gpus all -p 7860:7860 ghcr.io/ai-dock/stable-diffusion-webui:latest --sd15See also: SD hosting guide, all benchmark results, Whisper hosting for audio pipelines.
Deploy SD 1.5 on RTX 4060
Order this exact configuration. UK datacenter, full root access.
Order RTX 4060 Server
