Run Nemotron Cascade 2 on M4 Max

Yes — Nemotron Cascade 2 (30B) runs at 28 tok/s on M4 Max with 48 GB RAM using Q4_K_M quantization via MLX. First token latency is 1.2s. NVIDIA's Nemotron Cascade 2, a hybrid SSM-Transformer 30B model.

Speed
28
tok/s
First Token
1.2
seconds
RAM Needed
48
GB minimum
Engine
MLX
recommended
Want to run Nemotron Cascade 2 faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Nemotron Cascade 2 on M4 Max using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →

MetricValue
Tokens per second28 tok/s
Time to first token1.2s
QuantizationQ4_K_M
Minimum RAM48 GB
Recommended engineMLX
Parameters30B
Benchmark date2026-04

Q4_K_M 30B MLX M4 Max

Setup Guide: Run Nemotron Cascade 2 on M4 Max

The recommended engine for Nemotron Cascade 2 on M4 Max is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/nemotron-cascade-2-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run nemotron-cascade:2

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 35 tok/s 0.9s 64 GB Ollama
M4 Pro 22 tok/s 1.5s 24 GB Ollama

System Requirements

To run Nemotron Cascade 2 on M4 Max you need:

🛒 Get a Mac that runs Nemotron Cascade 2

Nemotron Cascade 2 needs about 48 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.

Compare More Models

See how Nemotron Cascade 2 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard