# Nemotron Cascade 2 30B-A3B: RAM and VRAM requirements

> Nemotron Cascade 2 30B-A3B is a 30B Nemotron 3 model (Mixture-of-Experts, 3B active per token). At Q4_K_M it needs about **25.1 GB** to run and fits **9 of 40** tracked devices. Minimum to run: Nvidia GeForce RTX 5090 (32GB).

Last validated: 2026-08-03. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 23.03 GB | ~25.1 GB |
| Q8_0 | 31.28 GB | ~33.4 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Apple M1 (8GB)** (8 GB): No, not enough memory
- **iPhone 17** (8 GB): No, not enough memory
- **iPhone 17 Pro** (12 GB): No, not enough memory
- **16GB RAM Laptop (CPU/iGPU only)** (16 GB): No, not enough memory
- **Google Pixel 10 Pro** (16 GB): No, not enough memory
- **Nvidia GeForce RTX 3090 (24GB)** (24 GB): No, not enough memory
- **Apple M4 Pro (48GB)** (48 GB): Yes, it runs
- **Apple M3 Ultra (256GB)** (256 GB): Yes, it runs (room for FP16)

Full table of all 40 devices: https://localmodel.run/model/nemotron-cascade-2-30b-a3b

## How to run
Quickest path: `ollama run nemotron-cascade-2:30b`. On Mac, LM Studio (ships MLX) is fastest; on Linux, Ollama for chat or vLLM to serve; on Windows, LM Studio or Ollama.

## Details
- Parameters: 30B (MoE, 3B active per token)
- Default context: 256k tokens
- License: nvidia-open-model-license (commercial use: conditional)
- Released: 2026-03
- HuggingFace: 48,235 downloads/mo, 522 likes

## FAQ
### How much VRAM or RAM does Nemotron Cascade 2 30B-A3B need?
About 25.1 GB at Q4_K_M (weights 23.03 GB + KV cache + overhead) at a 4k context. Budget ~33.4 GB for Q8_0.
### Can Nemotron Cascade 2 30B-A3B run on a laptop?
Nemotron Cascade 2 30B-A3B is large; you need a high-memory Mac or a 24 GB+ GPU at Q4_K_M.
### Can I use Nemotron Cascade 2 30B-A3B commercially?
Conditionally: NVIDIA Open Model License; check the terms for commercial use..

Sources: https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B, https://huggingface.co/bartowski/nvidia_Nemotron-Cascade-2-30B-A3B-GGUF, https://ollama.com/library/nemotron-cascade-2/tags
More: https://localmodel.run/model/nemotron-cascade-2-30b-a3b