No — not on this device

Nemotron 3 Super 120B-A12B at Q4_K_M needs 70.4 GB against 10.7 GB usable, and the shortfall of 59.7 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? →

The VRAM budget

weights 69.7 GB

Weights 69.7 GB KV cache @ 8K 0.06 GB Runtime overhead 0.6 GB Over budget 59.7 GB past 10.7 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	122.7 GB	123.4 GB	—	~1.5	−0.1% ppl	112.7 GB over
Q6_K	94.7 GB	95.4 GB	—	~1.9	−0.4% ppl	84.7 GB over
Q5_K_M	81.8 GB	82.5 GB	—	~2.2	−0.8% ppl	71.8 GB over
Q4_K_M	69.7 GB	70.4 GB	—	~2.6	−1.9% ppl	59.7 GB over
Q3_K_M	56.4 GB	57.1 GB	—	~3.2	−5.4% ppl	46.4 GB over
Q2_K	48.4 GB	49.0 GB	—	~3.8	−15% ppl	38.3 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

llama.cpp LM Studio MLX

terminal

$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-BF16-4bit \
    --max-tokens 512 --prompt "Hello"

Apple's own array framework. The fastest path on Apple Silicon. More on MLX.

01Download is 69.7 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.

02macOS caps what the GPU may wire down at about 10.7 GB of 16 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

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