Fastino Nemotron 3.5 Super VL Finance
Fastino Nemotron 3.5 Super VL Finance is a 120B-parameter, 12B-active text model fine-tuned for financial reasoning, extraction, and research. Its published BF16 checkpoint is a merged model that combines the Nemotron 3.5 Super VL language backbone with Fastino’s finance adapter; the vision encoder is not included.
What it does
Use it to answer questions about financial documents and tables, extract numerical spans and financial entities, and conduct source-grounded financial research.
- Availability
- Published BF16 weights on Hugging Face
- Pricing model
- Not established
- Deployment
- Can be run with vLLM; about 247 GB required before runtime overhead
- Privacy
- Not established
- Licence
- Apache License 2.0
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- The model is specialized for financial reasoning, extraction, and research. [1]
`Fastino-Nemotron-3.5-Super-VL-Finance` is a 120B-parameter, 12B-active hybrid Mamba-Transformer mixture-of-experts model specialized for financial reasoning, extraction, and research.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model targets financial document reasoning, numerical question answering over filings and tables, and numeric span extraction. [1]
The model targets financial document reasoning, numerical question answering over filings and tables, numeric span extraction, financial entity recognition, conversational analysis, and source-grounded financial research.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The repository contains a ready-to-run merged checkpoint. [1]
The repository contains a ready-to-run merged checkpoint: the language backbone of the NVIDIA Nemotron 3.5 Super VL early-access checkpoint plus Fastino's combined-finance LoRA adapter.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The published BF16 weights require about 247 GB before runtime overhead. [1]
The published weights are BF16 and require about 247 GB before runtime overhead.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model's vision encoder is not included, and its modalities are text. [1]
* **Modalities:** Text (the vision encoder of the VL base is not included)
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is licensed under the Apache License 2.0. [1]
This model is licensed under the Apache License 2.0.
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/fastino/Fastino-Nemotron-3.5-Super-VL-Finance
Retrieved 2026-10-28 00:51 UTC
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-18 09:52 UTC | material change | capability, availability, deployment | Current |
| 1 | 2026-10-17 10:49 UTC | publication | None | Current |
In briefs
2- DeepSeek opens a real-time web search API Weekly brief 2026-W42
- DeepSeek adds web search for apps and updates its Flash model Daily brief 2026-10-17
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.