Nemotron 3 Super
NVIDIA · released Mar 10, 2026 · nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
- Type
- Open weightsCustom licence
- Params
- 124B
- Context
- 1M
about 750K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026Nemotron 3 Super is a large text-only model from NVIDIA with a one-million-token request limit and a restricted licence. It excels at coding among its measured skills, though creative writing lags well behind, and provider choice varies sharply in both speed and cost.
Pick this for long-context text work at one million tokens, or for coding workloads where it scores highest among its own measured arenas. Use it if you need high throughput and can route to the fastest host, or if you want budget entry pricing from the cheaper providers. Skip it if you need a permissive licence, creative writing quality, or guaranteed fast throughput regardless of which host you land on.
The case for it
- One-million-token request limit — the largest context window in its class among measured models.
- Coding is its standout capability, with a 106-point gap above its own creative writing score.
- Peak throughput of 124 tokens per second available from one host, with another at 87.
- Wide provider choice at competitive entry pricing from some hosts.
The case against it
- Creative writing is its clear weak point, the lowest of six measured arenas and 106 points below its coding score.
- Custom restricted licence, not Apache or MIT — check terms before commercial use or redistribution.
- Throughput varies dramatically by provider, from 6 to 124 tokens per second, with slower hosts also charging more.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)97th of 143 · 1360.8
CodingWriting and fixing code on its own
Arena Coding98th of 143 · 1409.7
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Nemotron 3 Super for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Nemotron 3 Super placed and give it no mark out of five.
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, which is why they get no rating.
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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 5 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.085 in / $0.40 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.085 / $0.40 | 1M | not measured | Unknown | Unknown | Unknown |
| DeepInfrabfloat16 | $0.085 / $0.40 | 262K | not measured | Unknown | Unknown | Unknown |
| DeepInfrabf16 | $0.085 / $0.40 | 262K | 87 tok/s | No | No | Confirmed |
| DigitalOcean Gradient | $0.21 / $0.46 | 1M | 9 tok/s | No | No | Confirmed |
| Nebius AI Studiofp4 | $0.30 / $0.90 | 262K | 126 tok/s | No | No | Confirmed |
DeepInfra
DigitalOcean Gradient
Nebius AI StudioAcross the 5 listings we hold: 3 say they do not train on prompts, 0 say they do and 2 do not say. 3 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrabfloat16 | |||
| DeepInfrabf16 | ✓ | ✓ | ✗ |
| DigitalOcean Gradient | ✓ | ✓ | ✓ |
| Nebius AI Studiofp4 | ✗ | ✓ | ✗ |
Tool calling: 3 of 5 listings say yes, 1 says no, 1 publishes no parameter list. JSON output: 4 of 5 listings say yes, 1 publishes no parameter list. Strict schema: 2 of 5 listings say yes, 2 say no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 3d ago
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.
- 1 of 5 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 5 listings do not say whether they train on prompts.
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
- Modality record
- text->text
- Catalogue slug
- nvidia-nemotron-3-super