NVIDIA Nemotron Cascade 2 30B-A3B

NVIDIA Nemotron Cascade 2 30B-A3B loads in 24 GB at Q6_K and is comfortable from 48 GB of memory, Macs included from the MacBook Pro M5 Pro 48GB. Below: the full memory math, the cheapest card that runs it well, and the fastest machine we track.

PARAMETERS
30B (3B active)
FORMAT
Q6_K
MIN MEMORY
36 GB
BEST FOR
Reasoning, Math, Agentic tasks

Memory math

Weights (Q6_K)
24 GB
+ KV cache (16k)
~4.0 GB
Total at 16k
~28.0 GB
Comfortable from
48 GB

KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).

Hardware snapshot

Cheapest GPU
~19 tok/s est. — ~$3,847 used (as of 2026-07-31)
Fastest
~93 tok/s est.
Runs on a Mac?
~30 tok/s est.

More Nemotron models

Frequently asked questions

How much memory does NVIDIA Nemotron Cascade 2 30B-A3B need?

24 GB for the Q6_K weights, plus ~4.0 GB of KV-cache at 16k context — about 28.0 GB total. Comfortable from 48 GB of VRAM or unified memory.

Does NVIDIA Nemotron Cascade 2 30B-A3B run on a Mac?

Yes — from the MacBook Pro M5 Pro 48GB (~30 tok/s est.). Unified memory means the RAM budget is the only limit.

What is the cheapest GPU for NVIDIA Nemotron Cascade 2 30B-A3B?

The AMD Ryzen AI Max+ 395 (Strix Halo) is the cheapest tracked card that runs NVIDIA Nemotron Cascade 2 30B-A3B comfortably — ~19 tok/s est. at ~$3,847 used (as of 2026-07-31).

Cite this page

ModelFit: NVIDIA Nemotron Cascade 2 30B-A3B — specs, memory math and hardware verdicts.
https://modelfit.io/models/nemotron-cascade-2-30b-a3b/ (dataset updated 2026-09-03, CC BY 4.0).