No — not on this device

Nemotron 3 Super 120B-A12B at Q4_K_M needs 70.4 GB against 25.6 GB usable, and the shortfall of 44.8 GB is more than 32 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.

Does not fit 8K context Q4_K_M · 69.7 GB NVIDIA Open Model Released Mar 2026 Not in the Ollama library

The open-training-data 120B. Same hybrid layout as Lightning, so 128K context costs under a gigabyte.

What hardware do I need for Nemotron 3 Super 120B-A12B? →

Fits instead: Nemotron 3.5 Lightning 30B-A3B (18.4 GB)

The VRAM budget

weights 69.7 GB
Weights 69.7 GB KV cache @ 8K 0.06 GB Runtime overhead 0.6 GB Over budget 44.8 GB past 25.6 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 122.7 GB 123.4 GB ~0.8 −0.1% ppl 97.8 GB over
Q6_K 94.7 GB 95.4 GB ~1.0 −0.4% ppl 69.8 GB over
Q5_K_M 81.8 GB 82.5 GB ~1.2 −0.8% ppl 56.9 GB over
Q4_K_M 69.7 GB 70.4 GB ~1.4 −1.9% ppl 44.8 GB over
Q3_K_M 56.4 GB 57.1 GB ~1.7 −5.4% ppl 31.5 GB over
Q2_K 48.4 GB 49.0 GB ~2.0 −15% ppl 23.4 GB over

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 8 of its 88 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.

How to run it

terminal
$ llama-server \
    -hf nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:Q4_K_M \
    -c 8192 -ngl 31

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 69.7 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02With no GPU, thread count matters more than clock. Start at one thread per physical core.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model