Written by Jakub Rusinowski · Last updated September 11, 2026
Model library → Nemotron Cascade 2 → Nemotron Cascade 2 70B (Unverified Listing)
UNVERIFIED — retained only because this URL has been live and holds inbound links. NVIDIA's Nemotron-Cascade 2 release is a single checkpoint, Nemotron-Cascade-2-30B-A3B (31.6B total / 3.5B active); no 70B Cascade 2 checkpoint appears on NVIDIA's Hugging Face organisation, in the Nemotron-Cascade 2 collection, or on Ollama. The figures below were published here without sources and should not be relied on. Use Nemotron-Cascade 2 30B-A3B above, or Nemotron 3 Super if you want a larger NVIDIA model.
Nemotron Cascade 2 70B (Unverified Listing) needs about 43 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 70 Billion (unverified) |
| Context window | 128,000 |
| Architecture | Hybrid SSM + Attention (Mamba2) |
| Provider | NVIDIA |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 64 GB |
| Record updated | 2026-09-11 |
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 23.0 GB | 23.8 GB | ~29 tok/s (est.) | Tight fit |
| Q3_K_M | 29.8 GB | 30.6 GB | ~3 tok/s (est.) | Offloads to system RAM (slow) |
| Q4_K_M | 42.3 GB | 43.1 GB | ~3 tok/s (est.) | Offloads to system RAM (slow) |
| Q5_K_M | 49.6 GB | 50.4 GB | ~2 tok/s (est.) | Offloads to system RAM (slow) |
| Q6_K | 57.4 GB | 58.2 GB | — | Won't fit |
| Q8_0 | 74.4 GB | 75.2 GB | — | Won't fit |
| F16 | 140.0 GB | 140.8 GB | — | Won't fit |
Want the memory numbers alone, at every quantization level and your own context length? Use the Nemotron Cascade 2 70B (Unverified Listing) VRAM calculator.
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.
The cheapest catalogued GPU that runs Nemotron Cascade 2 70B (Unverified Listing) is the Apple M5 Pro (64 GB).
Install Ollama, then run:
ollama run nemotron-cascade-2Weights on Hugging Face: nvidia/Nemotron-Cascade-2-70B-Instruct.
Best for: research, long context, workstation, batch inference.
← All Nemotron Cascade 2 models | VRAM calculator | Check your own hardware