NVIDIA · nemotron
Can I run nemotron-mini?
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
4.2B parameters4K contexttextNVIDIA AI Foundation Models Community License Agreement6 builds
nemotron-mini system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| nemotron-mini:4b-instruct-q4_0 | Q4_0 | 2.4 GB | ~3.8 GB(est.) |
| nemotron-mini:4b | Q4_K_M | 2.5 GB | ~4.0 GB(est.) |
| nemotron-mini:4b-instruct-q5_K_M | Q5_K_M | 2.8 GB | ~4.5 GB(est.) |
| nemotron-mini:4b-instruct-q6_K | Q6_K | 3.2 GB | ~5.0 GB(est.) |
| nemotron-mini:4b-instruct-q8_0 | Q8_0 | 4.2 GB | ~6.3 GB(est.) |
| nemotron-mini:4b-instruct-fp16 | F16 | 7.8 GB | ~11.6 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run nemotron-mini locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run nemotron-mini:4b-instruct-q4_0 - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about nemotron-mini
- How much VRAM do I need to run nemotron-mini?
- At 4K context, the smallest published build of nemotron-mini (Q4_0) needs roughly 3.8 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run nemotron-mini without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 3.8 GB of free RAM for the smallest build.
- How big is the nemotron-mini download?
- The smallest published build is 2.4 GB. There are 6 builds in total, the largest being 7.8 GB. Leave some extra free disk space beyond the download itself.
- How do I run nemotron-mini locally?
- Install Ollama, then run "ollama run nemotron-mini:4b-instruct-q4_0" in a terminal. The weights download on first use and an interactive session opens.
Will nemotron-mini run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026