Skip to content
Models / Kolibri 1 / Calculator

Kolibri 1 cost & VRAM calculator

What does Kolibri 1 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

Kolibri 1 runs an always-on thinking mode. Reasoning (thinking) tokens are billed at the output rate ($15.00/M), so count them here to see the thinking portion of your bill.

API cost for your workload

No per-token API provider pricing tracked for Kolibri 1 yet. For flagship list prices, see the generic calculator.

Can you run it locally?

YES - IT RUNS ON HARDWARE YOU CAN BUY

Kolibri 1 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 BF16
47.2t/s
NVIDIA DGX Station 748GB 748GB BF16
28.2t/s
8x RTX 3090 rack (192GB) 192GB BF16
26.4t/s
AMD Instinct MI300X (192GB) 192GB BF16
18.7t/s
Mac Studio M4 Ultra 192GB 192GB BF16
4.2t/s
Mac Studio M4 Ultra 512GB 512GB BF16
4.2t/s
Dual EPYC 9004 + 768GB DDR5-4800 768GB BF16
1.6t/s
Epyc + 512GB DDR4-3200 + 2x RTX 3090 560GB BF16
0.7t/s
Epyc + 512GB DDR4-2400 + 2x RTX 3090 560GB BF16
0.5t/s
BF16
156.2GB weights 156.2GB min 187.0GB 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