Can you run Nemotron 3 Super 120B A12B locally?

Nemotron 3 family · 2026 · 123.6B parameters (12B activated per token) · Hugging Face model card

How much VRAM does Nemotron 3 Super 120B A12B need at each quantization?

Nemotron 3 Super 120B A12B needs 82.0 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.

Hybrid Mamba/attention stack (nemotron_h) with only 2 KV heads; config also sets mamba_hidden/mamba_num_heads for the SSM layers. Ships a built-in MTP head.

Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (88 layers, 2 KV heads, 128 head dim). Source: HF-verified 2026-09-30 via plain api (gated=false safetensors.total=123611012096 params=123.61B ctx=262144 license=other repo=nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16@2dc98e2afe4face0e4ce40972a915c45368bd34a layers=88 hidden=4096 kv_heads=2 heads=32 vocab=131072). MoE: num_experts=512 num_experts_per_tok=22 active_params_b=12.0 (vendor model card (Total 120B, 12B active); config n_routed_experts=512, 22 per token). VRAM figures are documented calculations (Q4-class ~0.6 GB per B params, on active params for MoE rows), not measurements. release_date is the HF repo lastModified date observed on the verification pass. No tok/s or benchmark scores invented.

Which GPUs can run Nemotron 3 Super 120B A12B locally?

At Q4_K_M with a 4k context, Nemotron 3 Super 120B A12B needs 82.0 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.

Runs Nemotron 3 Super 120B A12B comfortably (25%+ VRAM headroom)

Minimum GPUs that fit Nemotron 3 Super 120B A12B at Q4_K_M

These GPUs hold the model but leave little headroom — keep contexts short.

Needs 2+ GPUs to run Nemotron 3 Super 120B A12B

One of these cards is too small on its own, but a pair (tensor or pipeline parallel, ~90% efficiency) covers the 82.0 GB requirement. See our multi-GPU guide for setup.

Can a Mac run Nemotron 3 Super 120B A12B?

Yes — these Apple Silicon machines fit Nemotron 3 Super 120B A12B at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.

Can Nemotron 3 Super 120B A12B run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for Nemotron 3 Super 120B A12B at Q4_K_M. Their memory bandwidth is far below discrete GPUs, so expect a fraction of desktop generation speed.

Which pre-built systems can run Nemotron 3 Super 120B A12B?

These mini PCs and workstations from our database fit Nemotron 3 Super 120B A12B at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.

Frequently asked questions