Models / Nemotron 3.5 Lightning / Calculator

Nemotron 3.5 Lightning cost & VRAM calculator

What does Nemotron 3.5 Lightning 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

Casual Power user Team of 5 Codebase task

API cost for your workload

No per-token API provider pricing tracked for Nemotron 3.5 Lightning yet. For flagship list prices, see the generic calculator.

Can you run it locally?

YES - IT RUNS ON HARDWARE YOU CAN BUY

Nemotron 3.5 Lightning 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

1342.6t/s

NVIDIA DGX Station 748GB 748GB Q4_K_M

801.5t/s

8x RTX 3090 rack (192GB) 192GB Q4_K_M

750.4t/s

4x RTX 5090 (128GB) 128GB Q4_K_M

718.2t/s

AMD Instinct MI300X (192GB) 192GB Q4_K_M

533.5t/s

4x RTX 4090 (96GB) 96GB Q4_K_M

404.0t/s

2x RTX 5090 (64GB) 64GB Q4_K_M

359.1t/s

2x RTX 3090 (48GB) 48GB Q4_K_M

187.6t/s

RTX PRO 6000 Blackwell (96GB) 96GB Q4_K_M

179.5t/s

Mac Studio M4 Ultra 192GB 192GB Q4_K_M

119.4t/s

Mac Studio M4 Ultra 512GB 512GB Q4_K_M

119.4t/s

MacBook Pro M5 Max 128GB 128GB Q4_K_M

67.1t/s

Dual EPYC 9004 + 768GB DDR5-4800 768GB Q4_K_M

46.2t/s

DGX Spark 128GB unified 128GB Q4_K_M

27.4t/s

Ryzen AI Max+ 395 128GB 128GB Q4_K_M

25.7t/s

Jetson AGX Orin 64GB 64GB Q4_K_M

20.5t/s

Epyc + 512GB DDR4-3200 + 2x RTX 3090 560GB Q4_K_M

20.5t/s

Epyc + 512GB DDR4-2400 + 2x RTX 3090 560GB Q4_K_M

15.4t/s

Q4_K_M

32.0GB weights 34.0GB min 40.0GB rec

Q8_0

58.0GB weights 62.0GB min 68.0GB rec

FP16

60.0GB weights 64.0GB min 72.0GB 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