What is Nemotron 3 Super 120B A12B good for?

Agent and high-volume work such as IT ticket automation. Open weights under the NVIDIA Nemotron Open Model License, servable on a single high-memory GPU.

When is Nemotron 3 Super 120B A12B not a good fit?

Image input: it is text only. Memory follows the full 120B parameters, not the 12B active, and no maximum output is published.

What is the cheapest way to run Nemotron 3 Super 120B A12B?

Hosted, unless you push serious volume. Geodd charges $0.09 in / $0.50 out per 1M tokens. The cheapest rental that fits is 8x RTX 3060 at $288 a month, which costs the same as about 2B tokens a month on that API.

Can I self-host Nemotron 3 Super 120B A12B?

Yes. The weights are released under the NVIDIA Nemotron Open Model License. At 4-bit it needs about 68 GB of GPU memory, which starts at roughly $288 a month on the cheapest rental that fits.

Open weights · NVIDIA Nemotron Open Model License

Nemotron 3 Super 120B A12B

A 120B LatentMoE hybrid from NVIDIA activating 12B per token, combining Mamba-2, MoE and attention layers with Multi-Token Prediction, under the NVIDIA Nemotron Open Model License.

Jump to: Specs Pricing Self-hosting Similar models FAQ More from Nvidia

Visit website Compare vs other LLMs →

Cheapest via Geodd

Input: $0.09 / 1M tokens
Output: $0.50 / 1M tokens

4 providers

Key Specifications

Context window: 1M tokens
Knowledge cutoff: Jun 2025
Released: Mar 2026
Parameters: 120B, 12B active
Inputs: Text

Capabilities Show details: Reasoning Thinks before it answers, always on or as a switchable mode. Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON.

Hosted API pricing

Input tokens M Output tokens M

Provider	Input / 1M tokens	Output / 1M tokens	Cached input / 1M	Cost at 10M in + 2M out
Geodd Cheapest	$0.09	$0.50		$1.90	View
DigitalOcean	$0.30	$0.65	$0.06	$4.30	View
Cloudflare	$0.50	$1.50		$8.00	View
Nvidia Creator	Open weights, no hosted price				View

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Nemotron 3 Super 120B A12B needs about 68 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX 3060 at about $288 a month.

That costs the same as roughly 2B tokens a month on Geodd's API. Self-hosting is more expensive below that volume.

Precision	Cheapest, 32K context	Cheapest, full 1M context
4-bitINT4 / FP4	8× RTX 3060 68 GB VRAM · $288/mo	8× RTX 3060 76 GB VRAM · $288/mo
8-bitFP8 / INT8	8× RTX 3090 122 GB VRAM · $806/mo	8× RTX 3090 130 GB VRAM · $806/mo
16-bitFP16 / BF16	8× RTX A6000 242 GB VRAM · $3,168/mo	8× RTX A6000 250 GB VRAM · $3,168/mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest Nemotron 3 Super 120B A12B by blended rate, each at its own cheapest provider.

Model	Blended / 1M	Input / 1M	Output / 1M	Context	Cutoff	vs Nemotron 3 Super 120B A12B
Gemini 2.5 Flash-Lite Google Cloud	$0.15	$0.10	$0.40	1M	Jan 2025	−5%
GPT-4.1 Nano OpenAI	$0.15	$0.10	$0.40	1M	Jun 2024	−5%
Ministral 3 8B Mistral	$0.15	$0.15	$0.15	256K		−5%
Qwen3.5-Flash Alibaba Cloud	$0.15	$0.10	$0.40	1M		−5%
Llama 3.2 11B Vision Meta	$0.155	$0.05	$0.68	128K	Dec 2023	−2%
Nemotron 3 Super 120B A12B This model Nvidia	$0.1583	$0.09	$0.50	1M	Jun 2025
Gemma 4 31B Google Cloud	$0.17	$0.13	$0.37	256K	Jan 2025	+7%
Qwen3-235B-A22B Instruct (2507) Alibaba Cloud	$0.1717	$0.09	$0.58	262K		+8%
Llama 3.3 70B Meta	$0.175	$0.13	$0.40	128K	Dec 2023	+11%
Hy3 Tencent	$0.1967	$0.13	$0.53	262K		+24%
Ministral 3 14B Mistral	$0.20	$0.20	$0.20	256K		+26%

Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Packet·ai

Our sponsor

B200 @ $3.75/h on demand

No contract, no spot interrupts, no cluster minimums

Full root SSH, web dashboard, CI/CD ready

Reserve Now

Frequently Asked Questions

What is Nemotron 3 Super 120B A12B good for?: Agent and high-volume work such as IT ticket automation. Open weights under the NVIDIA Nemotron Open Model License, servable on a single high-memory GPU.
When is Nemotron 3 Super 120B A12B not a good fit?: Image input: it is text only. Memory follows the full 120B parameters, not the 12B active, and no maximum output is published.
What is the cheapest way to run Nemotron 3 Super 120B A12B?: Hosted, unless you push serious volume. Geodd charges $0.09 in / $0.50 out per 1M tokens. The cheapest rental that fits is 8x RTX 3060 at $288 a month, which costs the same as about 2B tokens a month on that API.
Can I self-host Nemotron 3 Super 120B A12B?: Yes. The weights are released under the NVIDIA Nemotron Open Model License. At 4-bit it needs about 68 GB of GPU memory, which starts at roughly $288 a month on the cheapest rental that fits.

More from Nvidia

Model	Context	Cutoff	Input / 1M	Output / 1M
Nemotron 3 Nano 30B A3B Open weights	262K	Jun 2025	$0.05	$0.20
Nemotron 3 Ultra 550B A55B Open weights	1M	Sep 2025	$0.66	$2.64