Nemotron 3 Nano 30B A3B
NVIDIA · released Dec 4, 2025 · nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- Type
- Open weightsCustom licence
- Params
- 31.6B
- Context
- 262K
3B active per word · about 197K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026Nemotron 3 Nano is a compact text-only model from NVIDIA that uses a mixture-of-experts design with 3 billion active parameters out of 31.6 billion total. It is priced uniformly across all tracked providers and scores highest on coding tasks, though its creative writing lags well behind.
Pick this for low-cost text generation workloads where you need long context up to 262,144 tokens, or where efficient inference with a small active-parameter footprint matters more than top benchmark scores. Use it for coding assistance, its strongest measured skill. Skip it if you need image, video or audio input, if you require a permissive open licence like Apache or MIT, or if creative writing quality is central to your use case.
The case for it
- Only 3 billion active parameters out of 31.6 billion total — roughly one in ten parameters fires per token, making inference unusually efficient for the model's scale.
- Same low price at every tracked provider, with no premium for faster endpoints.
- Coding is its standout skill: its Arena Coding score sits about 47 points above its own general chat score.
The case against it
- Creative writing is its weakest measured skill, trailing its coding score by more than 114 points.
- Custom licence — not Apache 2.0 or MIT — so commercial terms and redistribution rights are unverified in our data.
- Text-to-text only; no image, video or audio input accepted.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)120th of 143 · 1315.3
CodingWriting and fixing code on its own
Arena Coding112th of 143 · 1362.7
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 Nano 30B A3B 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 Nano 30B A3B 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
Borderline fit on an estimated size. It leaves 1 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Comfortable fit
GeForce RTX 5090 · 32 GB
Room to spare. 9 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 2.2 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 6 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
- $0.050 in / $0.20 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.050 / $0.20 | 262K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp4 | $0.050 / $0.20 | 262K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp4 | $0.050 / $0.20 | 262K | 163 tok/s | No | No | Confirmed |
| Novita AI | $0.050 / $0.20 | 262K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp4 | $0.050 / $0.20 | 262K | 209 tok/s | No | No | Confirmed |
| Crusoefp8 | $0.050 / $0.20 | 262K | 280 tok/s | No | No | Confirmed |
DeepInfra
Novita AIAcross the 6 listings we hold: 3 say they do not train on prompts, 0 say they do and 3 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 | ✓ | ✓ | ✓ |
| DeepInfrafp4 | |||
| DeepInfrafp4 | ✓ | ✓ | ✗ |
| Novita AI | |||
| Novita AIfp4 | ✓ | ✓ | ✗ |
| Crusoefp8 | ✓ | ✓ | ✓ |
Tool calling: 4 of 6 listings say yes, 2 publish no parameter list. JSON output: 4 of 6 listings say yes, 2 publish no parameter list. Strict schema: 2 of 6 listings say yes, 2 say no, 2 publish no parameter list.
When we formed this view
Dates behind this page
Prices last checked 4d 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.
- 2 of 6 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.
- 3 of 6 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-Nano-30B-A3B-BF16
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- nvidia-nemotron-3-nano-30b-a3b