Written by Jakub Rusinowski · Last updated August 15, 2026
Yes, comfortably — you'll have ~23.5 GB of headroom running Nemotron 3 Super 120B-A12B at Q4_K_M (72.45 GB, ~126 tok/s (est.)) with room for up to 32K context.
| VRAM | 96 GB |
| Memory Bandwidth | 1792 GB/s |
| Quant | VRAM needed | Fits 96 GB? | Max context |
|---|---|---|---|
| F16 | 242.2 GB | ✗ No | — |
| Q8_0 | 129.7 GB | ✗ No | — |
| Q6_K | 100.6 GB | ✗ No | — |
| Q5_K_M | 87.3 GB | ✓ Yes | 16K |
| Q4_K_M | 74.7 GB | ✓ Yes | 32K |
| Q3_K_M | 53.4 GB | ✓ Yes | 64K |
| Q2_K | 41.7 GB | ✓ Yes | 128K |
VRAM needed assumes a 4K-token context with an f16 KV cache; “Max context” is the largest window that still fits in 96 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
| Nemotron 3 Super 120B-A12B | Q4_K_M · 72.45 GB · ~126 tok/s (est.) |
At 2 hrs/day, buying (~$8,565) beats renting at $0.77/hr after about 15.4 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
Yes, comfortably — you'll have ~23.5 GB of headroom running Nemotron 3 Super 120B-A12B at Q4_K_M (72.45 GB, ~126 tok/s (est.)) with room for up to 32K context.
Nemotron 3 Super 120B-A12B at Q4_K_M quantization (72.45 GB), estimated ~126 tokens/sec, up to 32K context.
← Can I Run It? | Nemotron 3 Super Model Page | NVIDIA RTX PRO 6000 Blackwell GPU Page | Check Your Hardware