Skip to content
Models / Clef-Omni / Calculator

Clef-Omni cost & VRAM calculator

What does Clef-Omni cost to run for your workload, and can you run it on your own hardware? Set your workload below - we compute per-provider API cost live and tell you honestly whether local hardware can run it.

Your workload

API cost for your workload

No per-token API provider pricing tracked for Clef-Omni yet. For flagship list prices, see the generic calculator.

Can you run it locally?

YES - IT RUNS ON HARDWARE YOU CAN BUY

Clef-Omni fits on individual rigs. Here's the hardware that runs it comfortably; the full per-quant VRAM matrix and tok/s estimates live on the model page.

4x H100 80GB (320GB) 320GB Q4_K_M
3505.1t/s
NVIDIA DGX Station 748GB 748GB Q4_K_M
2092.6t/s
8x RTX 3090 rack (192GB) 192GB Q4_K_M
1959.1t/s
4x RTX 5090 (128GB) 128GB Q4_K_M
1875.0t/s
AMD Instinct MI300X (192GB) 192GB Q4_K_M
1392.8t/s
4x RTX 4090 (96GB) 96GB Q4_K_M
1054.7t/s
2x RTX 5090 (64GB) 64GB Q4_K_M
937.5t/s
2x RTX 3090 (48GB) 48GB Q4_K_M
489.8t/s
Single RTX 5090 (32GB) 32GB Q4_K_M
468.7t/s
RTX PRO 6000 Blackwell (96GB) 96GB Q4_K_M
468.7t/s
Mac Studio M4 Ultra 192GB 192GB Q4_K_M
311.6t/s
Mac Studio M4 Ultra 512GB 512GB Q4_K_M
311.6t/s
MacBook Pro M5 Max 128GB 128GB Q4_K_M
175.2t/s
Dual EPYC 9004 + 768GB DDR5-4800 768GB Q4_K_M
120.5t/s
DGX Spark 128GB unified 128GB Q4_K_M
71.4t/s
Ryzen AI Max+ 395 128GB 128GB Q4_K_M
67.0t/s
Jetson AGX Orin 64GB 64GB Q4_K_M
53.6t/s
Epyc + 512GB DDR4-3200 + 2x RTX 3090 560GB Q4_K_M
53.6t/s
Epyc + 512GB DDR4-2400 + 2x RTX 3090 560GB Q4_K_M
40.2t/s
Q4_K_M
20.2GB weights 24.0GB min 32.0GB rec

Want the own-vs-rent payback (capex vs your monthly API bill)? The budget tool computes that against representative rigs.

Full model card API pricing table Generic token calculator