logo elektroda
logo elektroda
X
logo elektroda

New AI model from Nvidia available for download - LLM Nemotron 3 Nano tests on laptop

p.kaczmarek2  1 1197 Cool? (+4)
📢 Listen (AI):

TL;DR

  • Nemotron-3-nano-30b-a3b, Nvidia’s new thinking LLM, was tested locally on a laptop with electronics, logic, and programming tasks.
  • It uses a Mixture-of-Experts design with a Mamba-2 + Transformer hybrid, 30 billion parameters, and only 3-4 billion active during inference.
  • The model was run in Ollama on Windows; the download occupied about 23 GB, and Nvidia says it supports up to 1M tokens and commercial use.
  • It handled resistor decoding, LED resistor sizing, console-star graphics, and simple HTML+JS games, but hallucinated on TC74, Tasmota, and some logic details.
Generated by the language model.
Screenshot of NVIDIA's Nemotron-3-Nano-30B-A3B model page with training details
In this topic I will show how anyone can run the Nemotron 3 Nano on their own computer and then test it with all sorts of electronics and programming tasks. The Nemotron 3 Nano is a new thinking LLM model based on a Mixture-of-Experts architecture with a Mamba-2 + Transformer hybrid. The model has 30 billion parameters, but only about 3-4 billion are active during inference, significantly reducing the computational requirements.

Nemotron-3-nano-30b-a3b supports very long context (up to 1M tokens), several languages (German, French, Italian, etc.; no Polish) and released under the NVIDIA Open Model License. The model allows commercial use.

Information about the model used:
https://build.nvidia.com/nvidia/nemotron-3-nano-30b-a3b/modelcard
Online access:
https://build.nvidia.com/nvidia/nemotron-3-nano-30b-a3b


Running the model locally
Download Ollama:
https://ollama.com/
Ollama has had a normal Windows app for some time now. Just download, run, and we already have a windowed interface to talk to AI. You still need to add models within the same app, the easiest way is to download them by entering their name from the Ollama Library:
https://ollama.com/library
Nemotron 3 Nano model card with description and download count on online platform
The model is fresh, published over a week ago.
In this case I entered: nemotron-3-nano:30b . The model occupies approximately 23 GB:
Download progress bar for model: 0.1 GB of 22.6 GB (0%)
Once downloaded, you can move on to testing. It is really very simple.

Decoding the barcode of the resistors
To start with a task that I think every budding electronics engineer encounters - decoding resistors. At the same time, this task potentially requires basic processing ability, although here it could be argued that the AI model doesn't 'predict' but has only memorised every possible permutation of colours. This is difficult for me to assess.
I used our Electrode calculator for comparison:
https://www.elektroda.pl/calculators/4-band-resistor
Expected result:
4-band resistor with colors: red, red, orange, green
Nemotron managed the task:
Resistor color code interpretation table: red, red, orange, green
Resistor value calculation: red, red, orange, green 22 kΩ ±0.5%.


Inverse resistor test
Can AI determine the colours for given resistor parameters and then draw this in HTML+JS? Obviously the whole thing as a separate chat - no story.
Screenshot showing a 22kΩ resistor description with color bands: red, red, orange, green.
He managed to specify the colours, but did he draw?
JavaScript syntax error in browser console during 22 kΩ resistor generation.
Here, however, we have a small glitch. The code doesn't run - JS syntax error.


Resistor for LED
Now for the second classic task, although here too I have chosen a slightly less typical voltage. Calculating the resistor for the LED:
LED resistor calculator with values: 14.5 V supply, 2.4 V drop, 15 mA current
LED resistor calculation table; supply 14.5 V, forward voltage 2.4 V, current 15 mA
Not only did the model handle the task, it also tried to advise the selection of the actual resistor values from the series.
Table with LED resistor values and power dissipation calculation for 14.5 V supply



Path width for current
https://www.elektroda.pl/calculators/trace-width-calculator-internal
Stripline trace width calculator with input parameters and 0.280 mm result
Result of internal PCB trace width calculation: approx. 0.28 mm (≈ 11 mil)
PCB trace width calculation for 1A and ΔT 10°C using Equation (1)


Console stars
The next test was about programming. I tried to think of some relatively simple but also less typical tasks. I decided that the AI would have to create four rectangles from the stars in the console and display them against the letters 'B'.
Screenshot of a console grid with stars and Bs, showing a layout error and highlighted with a red question mark.
Code: C / C++
Log in, to see the code

It went very well - it works.
Four rectangles made of asterisks over a background of 'B' letters in debug console
Time to modify. Will the AI understand the context? I want each rectangle to be filled with each consecutive number.
Screenshot of AI chat interface with C++ rectangle code modification instructions
Works:
Console output showing digit rectangles over a background of letter B



Game in HTML+JS - palette
Now some simple game playing. Another exam task for a student. I have given a somewhat precise description, but it always helps when working with AI.
Screenshot showing AI-generated description of a Pong game in HTML and JS
Generated code:
Code: HTML, XML
Log in, to see the code

I am surprised, but it works - I have no complaints:



I have asked for a modification - adding an opponent:
Description of Pong mode with AI paddle added at top of screen
Well, sure the shortcomings are there. The opponent is across and in addition the ball sometimes gets blocked between the pallet and the wall, but still impressive.




Arduino and reading from the TC74
The TC74 is a very simple temperature sensor with an I2C interface. Reading the temperature from it comes down to reading a single byte. Does Nemotron know about this?
Table showing TC74 sensor pins and corresponding Arduino connections
The generated code, on the other hand...
Code: C / C++
Log in, to see the code

In my opinion, this is not a valid code. The byte read is simply the temperature, you do not need to multiply by 0.25. In addition, you only need to read one byte. I also don't like the address yet, although it depends on the TC74 version.


Classics - r letters in strawberry
This is a fairly common example, AI has trouble counting letters because it operates on tokens.
But it does wonder...
Chat window with AI analyzing how many “r” letters are in the word “Strawberry”
AI answer output: the word strawberry contains 3 letters r
Good! How about a less typical word now? This will check if he has strawberry in the learning data.
Chat window showing question about how many “r”s are in “contrafibularities”; answer: 2.
Successful.

Logical puzzles
Some puzzles that LLMs have problems with. Tricky tasks.
Screenshot showing a logic puzzle question and AI's detailed response
Successful, although a long time for the system to think about it:
Screenshot of AI chat interface solving logic puzzle with farmer and sheep
The second trick question:
This question is about counting legs - four monkeys are jumping on the bed, there are three hens on the floor. The bed has four legs. How many legs are on the floor? 3*2 + 4 = 10.
AI answer calculating floor legs in riddle with chickens and monkeys
LLM replied that 6. Discussable.... he did not include the bed legs, but supposedly he should. Additionally... wrong justification as to the monkeys he gave, they don't count because they are on the bed. However, I understand that the question is indeed vaguely worded and it can be argued that indeed the bed does not count.

Information about Tasmota
Tasmota is open source for IoT devices, does Nemotron know about it?
AI response to “what is tasmota?” showing a firmware explanation for ESP modules
There was a hallucination in my mind regarding the name. The rest reasonably ok:
Tasmota stack diagram showing hardware, firmware, and web configuration interface
With this JSON is debatable, unless he means cmnd API.
In general, the description pretty much matches the facts came out.

Polish language Polish language is not officially supported
Polish is not officially supported, but worth checking anyway.
AI chat interface with Polish questions and generated responses
Looks acceptable, only occasional language errors.
Table explaining Arduino platform components: hardware, IDE, language, and ecology

Short performance test on my old laptop
I made the presentations on an old Asus ROG series laptop. Specifications:
- Intel (R) Core(TM) i7-6700HQ CPU @ 2.60GHz
- 48 GB RAM
- GeForce GTX 1060M
The video shows what the Nemotron's live response generation looks like:




Summary
I may have taken too easy a task for this LLM, but for me the results are impressive. I didn't expect such a thing to run on my old 2018 laptop.
This model really gets to grips with the basics of electronics, logic and programming, although it lacks at least some general knowledge - it hallucinates about the TC74 communication protocol, the origin of the Tasmota name, some of its applications.
I can agree here with what Nvidia itself admits - this is a small and powerful model for agent systems, not Wikipedia.
Do you see any uses for this type of LLM model? Have you tested the Nemotron yet?

About Author
p.kaczmarek2
p.kaczmarek2 wrote 14451 posts with rating 12432 , helped 650 times. Been with us since 2014 year.

Comments

p.kaczmarek2 30 Dec 2025 11:38

The fun continues, although I'll soon rather be testing based on my own script querying each downloadable model from Ollama in turn. These 'thoughts' of the model are, in a way, quite .... frightening: ... [Read more]

FAQ

TL;DR: Nemotron 3 Nano runs locally: 30B parameters with ~3–4B active, 1M‑token context, ~23 GB via Ollama; “the results are impressive.” [Elektroda, p.kaczmarek2, post #21791664] Why it matters:** This FAQ helps laptop users quickly install, test, and judge Nvidia’s Nemotron 3 Nano for electronics, coding, and hobby projects.

Quick Facts

What is Nvidia Nemotron 3 Nano (30B a3b) in plain terms?

It’s a “thinking” large language model using a Mixture‑of‑Experts with a Mamba‑2 + Transformer hybrid. It activates only ~3–4B of its 30B parameters during inference, which cuts compute needs while keeping quality. It targets agent‑style tasks, not encyclopedic recall. [Elektroda, p.kaczmarek2, post #21791664]

Can I run Nemotron 3 Nano on Windows with Ollama?

Yes. Ollama now has a normal Windows app. You download Ollama, then add the model from the Ollama Library by entering nemotron-3-nano:30b. The thread shows it running interactively on a consumer laptop. [Elektroda, p.kaczmarek2, post #21791664]

How big is the download and what hardware did it run on in the test?

The Ollama pull consumed about 23 GB for nemotron-3-nano:30b. It produced live responses on an i7‑6700HQ laptop with 48 GB RAM and a GeForce GTX 1060M GPU, demonstrating practical local use. [Elektroda, p.kaczmarek2, post #21791664]

How do I install and chat with the model locally (3 steps)?

  1. Install Ollama for Windows and open the app.
  2. In Ollama, pull the model by name: nemotron-3-nano:30b.
  3. Start a new chat in the Ollama interface and prompt the model. [Elektroda, p.kaczmarek2, post #21791664]

Which languages work? Is Polish supported?

The model handled several European languages in testing and generated acceptable Polish, but Polish is not officially supported. Expect occasional language errors in Polish outputs despite usable results. [Elektroda, p.kaczmarek2, post #21791664]

How well does it decode resistor color bands?

It correctly decoded 4‑band resistors and matched values verified with an external calculator. It also proposed inverse mapping from value to colors, though an HTML/JS drawing attempt contained a syntax error. [Elektroda, p.kaczmarek2, post #21791664]

Can Nemotron generate working HTML/JS games?

Yes. It generated a playable paddle‑and‑ball game and then an opponent variant. The second version showed issues, like the opponent’s placement and occasional ball trapping near walls. “I have no complaints” on the first demo. [Elektroda, p.kaczmarek2, post #21791664]

Where did the model fail or hallucinate in the tests?

It hallucinated details for the TC74 protocol, mis‑explained Tasmota’s name and some uses, and produced a small JS syntax bug in a drawing task. These are classic edge cases for small local LLMs. [Elektroda, p.kaczmarek2, post #21791664]

Is it good for IoT topics like Tasmota?

It knew what Tasmota is and described features reasonably, but name origin and some applications were off. Treat IoT brand specifics as untrusted unless you verify. Use it to draft configs, then confirm details. [Elektroda, p.kaczmarek2, post #21791664]

How did it perform on Arduino and the TC74 temperature sensor?

It produced an Arduino sketch that read two bytes and scaled by 0.25 °C, which the tester flagged as incorrect. TC74 reading needs only one byte, and the address depends on variant. Verify datasheet logic. [Elektroda, p.kaczmarek2, post #21791664]

Does Nemotron handle logical puzzles and counting tasks?

It solved some tricky puzzles but stumbled on a leg‑count question by omitting bed legs and giving weak justification. Expect occasional reasoning slips on ambiguous wording. [Elektroda, p.kaczmarek2, post #21791664]

What does the 1M‑token context buy me on a laptop?

You can feed very long documents, logs, or multi‑file code to a single session. The Mixture‑of‑Experts design activates ~3–4B parameters, helping keep latency manageable on older hardware. [Elektroda, p.kaczmarek2, post #21791664]

Is the model okay for commercial projects?

Yes. It’s released under the NVIDIA Open Model License, and the thread notes commercial use is allowed. Still review license terms for your distribution scenario. [Elektroda, p.kaczmarek2, post #21791664]

What’s a good way to test electronics skills quickly?

Try three prompts: decode a resistor from colors, compute an LED series resistor, and calculate PCB trace width for a given current. Compare results with independent calculators to confirm. [Elektroda, p.kaczmarek2, post #21791664]

Will Nemotron replace web search for general knowledge?

No. The tester agreed with Nvidia’s positioning: it’s a small, powerful model for agent systems, “not Wikipedia.” Use it for workflows and coding, then verify facts. [Elektroda, p.kaczmarek2, post #21791664]

What are realistic use cases on an older 2018 laptop?

Local chat for coding helpers, electronics calculations, simple game or UI prototypes, language drafting in supported languages, and logic practice. The live video shows responsive output on i7‑6700HQ + GTX 1060M. [Elektroda, p.kaczmarek2, post #21791664]
Generated by the language model.
%}