Skip to content
Models / Nemotron 3 Diarization / Calculator

Nemotron 3 Diarization cost & VRAM calculator

What does Nemotron 3 Diarization 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 Nemotron 3 Diarization yet. For flagship list prices, see the generic calculator.

Can you run it locally?

YES - IT RUNS ON HARDWARE YOU CAN BUY

Nemotron 3 Diarization 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 Q8_0
67000.0t/s
NVIDIA DGX Station 748GB 748GB Q8_0
40000.0t/s
8x RTX 3090 rack (192GB) 192GB Q8_0
37448.0t/s
4x RTX 5090 (128GB) 128GB Q8_0
35840.0t/s
AMD Instinct MI300X (192GB) 192GB Q8_0
26624.0t/s
4x RTX 4090 (96GB) 96GB Q8_0
20160.0t/s
2x RTX 5090 (64GB) 64GB Q8_0
17920.0t/s
2x RTX 3090 (48GB) 48GB Q8_0
9362.0t/s
Single RTX 5090 (32GB) 32GB Q8_0
8960.0t/s
RTX PRO 6000 Blackwell (96GB) 96GB Q8_0
8960.0t/s
Mac Studio M4 Ultra 192GB 192GB Q8_0
5956.4t/s
Mac Studio M4 Ultra 512GB 512GB Q8_0
5956.4t/s
Single RTX 4090 (24GB) 24GB Q8_0
5040.0t/s
MacBook Pro M5 Max 128GB 128GB Q8_0
3349.1t/s
Single GTX 1080 Ti (11GB) 11GB Q8_0
2420.0t/s
Dual EPYC 9004 + 768GB DDR5-4800 768GB Q8_0
2304.0t/s
DGX Spark 128GB unified 128GB Q8_0
1365.0t/s
Ryzen AI Max+ 395 128GB 128GB Q8_0
1280.0t/s
Jetson AGX Orin 64GB 64GB Q8_0
1024.0t/s
Epyc + 512GB DDR4-3200 + 2x RTX 3090 560GB Q8_0
1024.0t/s
Epyc + 512GB DDR4-2400 + 2x RTX 3090 560GB Q8_0
768.0t/s
NVIDIA Jetson Orin NX 16GB 16GB Q8_0
512.0t/s
Q8_0
0.1GB weights 0.2GB min 1.0GB rec
BF16
0.2GB weights 0.3GB min 1.0GB 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