Can I Run Nemotron Cascade 2 on NVIDIA L40S?
Written by Jakub Rusinowski · Last updated September 11, 2026
Yes, but it's tight — Nemotron Cascade 2 70B at Q4_K_M needs 45.4 GB at 8K context (42.3 GB weights + 3.1 GB KV cache/overhead), leaving ~2.6 GB of the NVIDIA L40S's 48 GB, at ~18 tok/s (est.), with room for up to 16K context.
See what else this hardware can run →
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
NVIDIA L40S Specs
| VRAM | 48 GB |
| Memory Bandwidth | 864 GB/s |
Nemotron Cascade 2 70B on the NVIDIA L40S: VRAM by quantization
| Quant | VRAM needed | Fits 48 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 143.2 GB | ✗ No | — | — |
| Q8_0 | 77.6 GB | ✗ No | — | — |
| Q6_K | 60.6 GB | ✗ No | — | — |
| Q5_K_M | 52.8 GB | ✗ No | — | — |
| Q4_K_M | 45.4 GB | ✓ Yes | 16K | — |
| Q3_K_M | 33 GB | ✓ Yes | 32K | — |
| Q2_K | 26.2 GB | ✓ Yes | 64K | — |
Assumes an 8K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 48 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA L40S: 8K 45.4 GB · 32K 52.6 GB ✗ · 125K 80.3 GB ✗. Past 32K it no longer fits 48 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
No compatible GPU? Nemotron Cascade 2 on 24 GB of system RAM, CPU only: runs.
Nemotron Cascade 2 Sizes That Fit the NVIDIA L40S (at 8K context)
| Nemotron Cascade 2 70B | Q4_K_M · 45.4 GB at 8K context · ~18 tok/s (est.) |
| Nemotron-Cascade 2 30B-A3B | Q4_K_M · 21.7 GB at 8K context · ~166 tok/s (est.) |
At 2 hrs/day, buying (~$7,499) beats renting at $0.77/hr after about 13.5 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.
FAQ
Is the NVIDIA L40S enough to run Nemotron Cascade 2 locally?
Yes, but it's tight — Nemotron Cascade 2 70B at Q4_K_M needs 45.4 GB at 8K context (42.3 GB weights + 3.1 GB KV cache/overhead), leaving ~2.6 GB of the NVIDIA L40S's 48 GB, at ~18 tok/s (est.), with room for up to 16K context.
What's the best Nemotron Cascade 2 size for the NVIDIA L40S?
Nemotron Cascade 2 70B at Q4_K_M quantization needs 45.4 GB at 8K context (42.3 GB weights + 3.1 GB KV cache/overhead), estimated ~18 tokens/sec, up to 16K context.
Nemotron Cascade 2 on Other GPUs
- Nemotron Cascade 2 on NVIDIA RTX 6000 Ada Generation
- Nemotron Cascade 2 on Apple M3 Pro
- Nemotron Cascade 2 on NVIDIA GeForce RTX 5090
- Nemotron Cascade 2 on Apple M4
- Nemotron Cascade 2 on Apple M2 Pro
Popular Models on the NVIDIA L40S
VRAM Tier
Troubleshooting
- CUDA out of memory — why it happens and how to fix it
- Which GGUF quant should I download? (Q4 vs Q5 vs Q8)
Buying Guide
← Can I Run It? | Nemotron Cascade 2 Model Page | NVIDIA L40S GPU Page | VRAM calculator | Check Your Hardware