Nemotron 3.5 Lightning 30B-A3B

Nemotron 3.5 Lightning 30B-A3B loads in 23.7 GB at Q4_K_M and is comfortable from 36 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
Q4_K_M
MIN MEMORY
36 GB
BEST FOR
Agentic, Coding, Long context

Memory math

Weights (Q4_K_M)
23.7 GB
+ KV cache (16k)
~0.1 GB
Total at 16k
~23.8 GB
Comfortable from
36 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
~26 tok/s est. — ~$3,847 used (as of 2026-07-31)
Fastest
~125 tok/s est.
Runs on a Mac?
~42 tok/s est.

Go deeper

Best hardware for Nemotron 3.5 Lightning 30B-A3B: cheapest, best value, fastest

More Nemotron models

NVIDIA Nemotron Cascade 2 30B-A3BNVIDIA Nemotron 3 Ultra

Frequently asked questions

How much memory does Nemotron 3.5 Lightning 30B-A3B need?

23.7 GB for the Q4_K_M weights, plus ~0.1 GB of KV-cache at 16k context — about 23.8 GB total. Comfortable from 36 GB of VRAM or unified memory.

Does Nemotron 3.5 Lightning 30B-A3B run on a Mac?

Yes — from the MacBook Pro M5 Pro 48GB (~42 tok/s est.). Unified memory means the RAM budget is the only limit.

What is the cheapest GPU for Nemotron 3.5 Lightning 30B-A3B?

The AMD Ryzen AI Max+ 395 (Strix Halo) is the cheapest tracked card that runs Nemotron 3.5 Lightning 30B-A3B comfortably — ~26 tok/s est. at ~$3,847 used (as of 2026-07-31).

Cite this page

ModelFit: Nemotron 3.5 Lightning 30B-A3B — specs, memory math and hardware verdicts.
https://modelfit.io/models/nemotron-3.5-lightning-30b/ (dataset updated 2026-09-03, CC BY 4.0).