- Size
- 8.9B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, NVIDIA Open Model License AgreementOur reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 12 Aug 2025the date the repo was created
- Context length
- 128k tokensfrom the model's config
- Fine-tune
- of nvidia/NVIDIA-Nemotron-Nano-12B-v2NemotronHForCausalLM
- On Hugging Face
- nvidia/NVIDIA-Nemotron-Nano-9B-v2172k downloads in the last 30 days, 533 likes
Scores
- default setting0.0%via Epoch AI
Epoch's name: nvidia-nemotron-nano-9b-v2. Best closed model on this set: gemini-4-carbon_high, 36.0% (Google DeepMind). All 271 results
- default setting25.0%Fiction.live leaderboard
Epoch's name: nvidia-nemotron-nano-9b-v2. Best closed model on this set: gpt-5-2025-08-07_medium, 97.2% (OpenAI). All 61 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.13 GB, worked out from the model's config (nvidia/NVIDIA-Nemotron-Nano-9B-v2), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF (converted by bartowski), 20k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 4.7 GBfile size | 5.4 GB4.7 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ3_XXSOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ3_XXSDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-IQ3_XXS.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| IQ3_XS | 4.8 GBfile size | 5.4 GB4.8 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ3_XSOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ3_XSDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-IQ3_XS.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q3_K_S | 4.8 GBfile size | 5.4 GB4.8 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q3_K_SOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q3_K_SDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q3_K_S.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| IQ3_M | 4.9 GBfile size | 5.5 GB4.9 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ3_MOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ3_MDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-IQ3_M.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| IQ4_XS | 4.9 GBfile size | 5.5 GB4.9 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ4_XSOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ4_XSDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-IQ4_XS.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| IQ4_NL | 4.9 GBfile size | 5.6 GB4.9 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ4_NLOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:IQ4_NLDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-IQ4_NL.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q4_0 | 5.0 GBfile size | 5.6 GB5.0 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_0Ollama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_0Download hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q4_0.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q3_K_M | 5.0 GBfile size | 5.6 GB5.0 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q3_K_MOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q3_K_MDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q3_K_M.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q3_K_L | 5.1 GBfile size | 5.7 GB5.1 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q3_K_LOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q3_K_LDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q3_K_L.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q3_K_XL | 5.4 GBfile size | 6.0 GB5.4 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q3_K_XLOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q3_K_XLDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q3_K_XL.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q4_1 | 5.4 GBfile size | 6.1 GB5.4 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_1Ollama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_1Download hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q4_1.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q4_K_S | 5.8 GBfile size | 6.4 GB5.8 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_K_SOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_K_SDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q4_K_S.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q4_K_M | 6.1 GBfile size | 6.7 GB6.1 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_K_MOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_K_MDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q4_K_M.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q4_K_L | 6.3 GBfile size | 6.9 GB6.3 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_K_LOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q4_K_LDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q4_K_L.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q5_K_S | 6.3 GBfile size | 6.9 GB6.3 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q5_K_SOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q5_K_SDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q5_K_S.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q5_K_M | 6.6 GBfile size | 7.2 GB6.6 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q5_K_MOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q5_K_MDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q5_K_M.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q5_K_L | 6.8 GBfile size | 7.4 GB6.8 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q5_K_LOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q5_K_LDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q5_K_L.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q6_K | 8.5 GBfile size | 9.1 GB8.5 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q6_KOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q6_KDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q6_K.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q6_K_L | 8.5 GBfile size | 9.1 GB8.5 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q6_K_LOllama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q6_K_LDownload hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q6_K_L.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| Q8_0 | 8.8 GBfile size | 9.4 GB8.8 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q8_0Ollama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:Q8_0Download hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-Q8_0.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
| BF16 | 16.6 GBfile size | 17.2 GB16.6 + 0.13 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:BF16Ollama ollama run hf.co/bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF:BF16Download hf download bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF --include "nvidia_NVIDIA-Nemotron-Nano-9B-v2-bf16.gguf" --local-dir nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 16.6 GBfile size | 17.2 GB16.6 + 0.13 + 0.50 |
hf download nvidia/NVIDIA-Nemotron-Nano-9B-v2 --local-dir NVIDIA-Nemotron-Nano-9B-v2Other conversions (6; sizes not read)
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8 FP8, by the maker, 192k downloads
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4 NVFP4, by the maker, 41k downloads
- litert-community/NVIDIA-Nemotron-Nano-9B-v2 Other, 591 downloads
- cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit AWQ, 4bit, 129 downloads
- cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-8bit AWQ, 8bit, 43 downloads
- liodon-ai/NVIDIA-Nemotron-Nano-9B-v2-FP8 FP8, 30 downloads
The Hub tags 22 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Fine-tunes of this model
Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.
- nvidia/NVIDIA-Nemotron-3-Nano-4B-BF164.0B1.2MReviewed
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese8.9B3.1kUnreviewed
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.