Dataset updated 2026-11-12Nemotron 3 Super 120B-A12B
Nemotron 3 Super 120B-A12B loads in 86.8 GB at Q4_K_M and decodes at the speed of its 12B active path, comfortably from 128 GB of memory, Macs included, starting at the MacBook Pro M5 Max 128GB. Below is the memory math we ran for it, the smallest card that fits, and the fastest machine we track.
- Parameters
- 120B(12B active)
- Format
- Q4_K_M
- Min memory
- 128 GB
- Best for
- Agentic workflows, Long context, Reasoning
How much memory does Nemotron 3 Super 120B-A12B need?
Nemotron 3 Super 120B-A12B is a 120B mixture-of-experts model (12B active per token) built for agentic workflows, long context, reasoning. The weights alone take 86.8 GB at Q4_K_M; add context and the OS, and it belongs in the 128 GB memory class. Every number below comes from the ModelFit engine: speeds are estimates, labeled est., because we do not benchmark hardware ourselves.
KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).
Which machines run Nemotron 3 Super 120B-A12B?
- Smallest GPU
- AMD Ryzen AI Max+ 395 (Strix Halo)est. 13 tok/s · 110 GB VRAMtypical error 25%
- Fastest
- Mac Studio M5 Ultra 256GBest. 61 tok/stypical error 10%
- Runs on a Mac?
- MacBook Pro M5 Max 128GBest. 33 tok/stypical error 10%
Verdicts come from the same engine that powers our fit checker: memory capacity first, bandwidth for speed. How we compute these numbers · What typical error means · Hugging Face model card
Go deeper
- Also tracked: Nemotron 3 Super 120B-A12B (IQ4_XS)(IQ4_XS, 64.5 GB, min 96 GB)
More Nemotron models
5 pagesGet told when a better model fits your MacBook Air M5 16 GB
Get one email when a new open-weight model is a better fit for this machine.
For: MacBook Air M5 16 GB
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Config reports
No speed test run for this model yet. Run the speed test: npx @modelfit/cli@latest bench
Share your config
Frequently asked questions
How much memory does Nemotron 3 Super 120B-A12B need?
86.8 GB for the Q4_K_M weights, plus ~0.1 GB of KV-cache at 16k context, about 86.9 GB total. Comfortable from 128 GB of VRAM or unified memory.
Does Nemotron 3 Super 120B-A12B run on a Mac?
Yes, from the MacBook Pro M5 Max 128GB (est. 33 tok/s, typical error 10%). Unified memory means the RAM budget is the only limit.
What is the smallest GPU for Nemotron 3 Super 120B-A12B?
The AMD Ryzen AI Max+ 395 (Strix Halo) (110 GB VRAM) is the smallest tracked card that runs Nemotron 3 Super 120B-A12B comfortably, est. 13 tok/s, typical error 25%.
Cite this page
ModelFit: Nemotron 3 Super 120B-A12B, specs, memory math and hardware verdicts. https://modelfit.io/models/nemotron-3-super-120b/ (dataset updated 2026-11-12, CC BY 4.0).