Written by Jakub Rusinowski · Last updated July 10, 2026
NVIDIA's consumer-friendly hybrid SSM+attention model released March 2026. The 30B variant fits in a single RTX 4060 Ti (17 GB Q4) and sustains ~54 tokens/second — faster than any pure-Transformer of comparable quality. Uses selective state-space layers (Mamba2) to process long contexts 3x cheaper than attention. Apache 2.0 licensed and available on Ollama.
| Nemotron Cascade 2 30B | Min 19 GB VRAM · Q4_K_M · 128,000 ctx · ollama run nemotron-cascade:30b |
| Nemotron Cascade 2 70B | Min 43 GB VRAM · Q4_K_M · 128,000 ctx · ollama run nemotron-cascade:70b |
The cheapest GPU that runs Nemotron Cascade 2 locally (min 19 GB VRAM) is the AMD Radeon RX 7900 XT (20 GB).
Install Ollama then run: ollama run nemotron-cascade:30b
Minimum VRAM: 19 GB. For best results use Q4_K_M quantization.
Nemotron Cascade 2 needs about 19 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Nemotron Cascade 2 30B (19 GB, Q4_K_M); Nemotron Cascade 2 70B (43 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Nemotron Cascade 2 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Nemotron Cascade 2 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run nemotron-cascade:30b. This downloads Nemotron Cascade 2 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.