Nemotron 3 Super
NVIDIA · released Mar 10, 2026 · nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
- Type
- Open weightsCustom licence
- Params
- 124B
- Context
- 1M
active per word not recorded by us · about 750K words of context · download allowed, licence restricts use
Our take
The case for it
- Long inputs need not be split up first: a long report or a stack of documents can go in beside the question, though whether it recalls material across all of it is unverified in our data.
- You can download it and run it on your own hardware rather than depending on a host.
The case against it
- Lower-half placings on every board we hold, including 119th of 168 on Arena Text (overall) and 128th of 168 on Arena Creative Writing as of 25 Sep 2026 — boards that record which answer people preferred, not whether it was correct.
- The custom licence puts conditions on commercial use and redistribution, so it needs reading before you build on it.
How good is it?
An open text model for everyday questions and code, though drafting and prose are not its strong suit.
- drafts, rewrites and editingArena Creative Writing · 128th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)119th of 168 · 1360
CodingWriting and fixing code on its own
Arena Coding121st of 168 · 1407
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing128th of 168 · 1303
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M1 Ultra (64-core GPU) · 128 GB
Room to spare. 14.4 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
The only listing at 262K of context — the other 2 in the table below are not like-for-like. One cheaper row there is outside that comparison: a different quantisation.
- per 1M tokens
- $0.080 in / $0.45 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| DeepInfrabf16Direct and through OpenRouter | $0.085 / $0.40checked 4 hours ago | 262K16K max reply through OpenRouter | 71 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| OpenRouterOpenRouter's own listing | $0.080 / $0.45checked 4 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| DekaLLMfp8Through OpenRouter | $0.080 / $0.45checked 4 hours ago | 262K236K max reply | 27 tok/s | No | No | Confirmed |
DeepInfraAcross the 3 listings we hold: 2 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check (1 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| DeepInfrabf16Direct and through OpenRouter | ✓ | ✓ | ✗ |
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| DekaLLMfp8Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 2 of 3 listings say yes, 1 says no.
When we formed this view
Recent changes
What moved
input +82% ($0.165 → $0.300 per 1M tokens), output +82% ($0.357 → $0.650 per 1M tokens)What moved
input −21% ($0.210 → $0.165 per 1M tokens), output −21% ($0.4550 → $0.3575 per 1M tokens)What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- nvidia-nemotron-3-super