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
The case for it
- Cheap to run at volume: the lowest listed offers sit well under the rates of the mid-size models here, which keeps high-volume extraction and classification affordable.
- Realistic on one machine: about 3 billion of its 31.6 billion parameters work per token, so memory in use is closer to a small model than a mid-size one.
- Long documents need not be split first — the request capacity takes a long report or a stack of documents beside the question, though reliable recall across all of it is unverified in our data.
The case against it
- Measured quality is weak across every board we hold: 143rd of 168 on Arena Text (overall) as of 25 Sep 2026, and 137th of 168 on Arena Coding as of 25 Sep 2026 — preference votes rather than correctness checks.
- The custom licence puts conditions on commercial use and redistribution, so it needs reading before you build on it.
- Text in, text out: no image, audio or video input, so anything visual has to be described in words first.
How good is it?
An open text model for general chat, drafting and code, though it trails most models on those everyday tasks.
- getting answers to everyday questionsArena Text (overall) · 143rd of 168
- drafts, rewrites and editingArena Creative Writing · 151st of 168
- writing and completing codeArena Coding · 137th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)143rd of 168 · 1313
CodingWriting and fixing code on its own
Arena Coding137th of 168 · 1361
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 Writing151st of 168 · 1241
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
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.
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.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.050 / $0.20checked 4 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp4Direct and through OpenRouter | $0.050 / $0.20checked 4 hours ago | 262K228K max reply through OpenRouter | 29 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Novita AIfp4Direct and through OpenRouter | $0.050 / $0.20checked 4 hours ago | 262K33K max reply through OpenRouter | 216 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Crusoefp8Through OpenRouter | $0.050 / $0.20checked 4 hours ago | 262K236K max reply | 108 tok/s | No | No | Confirmed |
| Nebius AI Studiofp8Through OpenRouter | $0.060 / $0.24checked 4 hours ago | 262K236K max reply | 126 tok/s | No | No | Confirmed |
DeepInfra
Novita AI
Nebius AI StudioAcross the 5 listings we hold: 4 say they do not train on prompts (2 of them only through OpenRouter), 0 say they do and 1 does not say. 4 appear in the zero-retention registry we check (2 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 |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| DeepInfrafp4Direct and through OpenRouter | ✓ | ✗ | ✗ |
| Novita AIfp4Direct and through OpenRouter | ✓ | ✓ | ✗ |
| Crusoefp8Through OpenRouter | ✓ | ✓ | ✓ |
| Nebius AI Studiofp8Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 5 of 5 listings say yes. JSON output: 4 of 5 listings say yes, 1 says no. Strict schema: 3 of 5 listings say yes, 2 say no.
When we formed this view
Recent changes
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.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings does not say whether it trains on prompts, and 2 answer only through OpenRouter, not for their own listing.
- 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-Nano-30B-A3B-BF16
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- nvidia-nemotron-3-nano-30b-a3b