- Size
- 124B parameters, 12.0B active (from the repo name)counted from the safetensors header on the Hub
- Licence
- custom, read it, OpenMDW License Agreement, version 1.1Our 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 Oct 2026the date the repo was created
- Context length
- 1M tokensas an API provider reports it
- Kind
- Base model (no base model declared on the Hub)NemotronH_Omni_Reasoning_V3
- On Hugging Face
- nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF1685k downloads in the last 30 days, 133 likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
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.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 4.0 GB, a rough allowance by model size, because we do not have this model's attention config. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF (converted by DevQuasar), 637 downloads. Sizes are the real files on the Hub, all parts added up. For image input you also need the projector file mmproj-nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16.f16.gguf (1.6 GB), not counted below.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 49.8 GBfile size, 4 parts | 54.3 GB49.8 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF:Q2_KDownload hf download DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF --include "Q2_K/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16.f16.gguf.Q2_K.gguf-*-of-00004.gguf" --local-dir nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF |
| Q3_K_M | 62.6 GBfile size, 5 parts | 67.1 GB62.6 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF:Q3_K_MDownload hf download DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF --include "Q3_K_M/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16.f16.gguf.Q3_K_M.gguf-*-of-00005.gguf" --local-dir nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF |
| Q4_K_M | 80.1 GBfile size, 7 parts | 84.6 GB80.1 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF:Q4_K_MDownload hf download DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF --include "Q4_K_M/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16.f16.gguf.Q4_K_M.gguf-*-of-00007.gguf" --local-dir nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF |
| Q5_K_M | 89.1 GBfile size, 8 parts | 93.6 GB89.1 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF:Q5_K_MDownload hf download DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF --include "Q5_K_M/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16.f16.gguf.Q5_K_M.gguf-*-of-00008.gguf" --local-dir nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF |
| Q6_K | 105.2 GBfile size, 9 parts | 109.7 GB105.2 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF:Q6_KDownload hf download DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF --include "Q6_K/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16.f16.gguf.Q6_K.gguf-*-of-00009.gguf" --local-dir nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF |
| Q8_0 | 119.6 GBfile size, 10 parts | 124.1 GB119.6 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF:Q8_0Download hf download DevQuasar/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF --include "Q8_0/nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16.f16.gguf.Q8_0.gguf-*-of-00010.gguf" --local-dir nvidia.NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 231.8 GBfile size | 236.3 GB231.8 + 4.0 + 0.50 |
hf download nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 --local-dir NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16The Hub tags 37 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
9 providers serve this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| Crusoe | $0.10 | $0.40 | 1M | bf16 | 78 | 1.0 s | 99.5% | yes | yes |
| CoreWeave | $0.15 | $0.47 | 1M | nvfp4 | 399 | 0.6 s | 100.0% | yes | yes |
| basetenserves nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 | $0.20 | $0.50 | 1M | not given | 286 | 0.3 s | ? | yes | yes |
| BaseTen | $0.20 | $0.50 | 1M | fp4 | 341 | 1.1 s | 99.9% | yes | no |
| DeepInfra | $0.15 | $0.50 | 256k | fp4 | 249 | 0.7 s | 99.8% | yes | yes |
| PrimeIntellect | $0.15 | $0.50 | 1M | nvfp4 | 179 | 1.7 s | 97.6% | yes | yes |
| Together | $0.15 | $0.50 | 256k | not given | 141 | 0.8 s | 100.0% | yes | yes |
| Venice | $0.20 | $0.50 | 256k | fp4 | 369 | 0.3 s | 100.0% | yes | yes |
| Nebius | $0.30 | $0.90 | 1M | fp4 | 102 | 2.9 s | 99.8% | yes | yes |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:crusoe", "messages": [{"role": "user", "content": "Hello"}]}'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-3.5-Bolt-74B-A9B-BF1674.9B8.7kUnreviewed
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.