# Fastino-Nemotron-3.5-Lightning-Finance by Fastino Source: https://savrn.com/models/fastino-nemotron-3-5-lightning-finance Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Fastino-Nemotron-3.5-Lightning-Finance (31.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 63.2 GB | 75.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 31.6 GB | 37.9 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 15.8 GB | 18.9 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026. [Fastino-Nemotron-3.5-Lightning-Finance on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/fastino-nemotron-3-5-lightning-finance/gpus) ## Model Card By Fastino, published under apache-2.0, revision 157ebab9a11f. Fastino-Nemotron-3.5-Lightning-Finance is a 30B-parameter, 3B-active mixture-of-experts model specialized for financial reasoning, extraction, and research fine-tuned on LoRA with the Fastino Fine-Tuning Agent. - Developed by: Fastino Labs, in collaboration with NVIDIA - Base checkpoint: NVIDIA Nemotron 3.5 Lightning, July 29, 2026 release - Post-training checkpoint: Fastino-Finance - License: Apache 2.0 - Language: English - Modalities: Text - Model Release Blog: [Release Blog](https://fastino.ai/blog/fastino-nemotron-3-5-lightning-finance-and-healthcare/) - Fine-Tuning Agent: [Private Preview](https://fastino.ai/agent) - Research: [Fastino Fine-Tuning Agent](https://arxiv.org/abs/2604.09791) ### What it is designed for 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. The evaluation suite includes FinQA, TAT-QA, SEC-Num, FinEntity, BizFinBench, BigFinanceBench, ConvFinQA, and FiQA. ### Quickstart The published weights are BF16 and require about 66 GB before runtime overhead. An 80 GB or larger GPU, or tensor parallelism across multiple GPUs, is recommended. ``` pip install "vllm==0.23.0" ``` [Read the full model card (576 words)](https://savrn.com/models/fastino-nemotron-3-5-lightning-finance/card) ## Configuration Architecture NemotronHForCausalLM Context length (tokens) 262,144 Layers 52 Hidden size 2,688 Feed-forward size 1,856 Attention heads 32 Key/value heads 2 Head dimension 128 Vocabulary size 131,072 Routed experts 128 Experts active per token 6 RoPE base 10,000 Model type nemotron_h ## Identity and Version Repository fastino/Fastino-Nemotron-3.5-Lightning-Finance Publisher Fastino Task Text generation Modality Text Library transformers Parameters 31.6B parameters Languages en Revision 157ebab9a11f58672d43fb69847ff67db8f8e63d First published 2026-08-06 Last updated 2026-09-17 ## Files and Weights 27 files, 65.9 GB in total. The weights are 14 files totalling 65.8 GB in safetensors. Weights14 files · 65.8 GB Configuration6 files · 646.1 KB Tokenizer2 files · 17.3 MB Documentation1 file · 6.5 KB Other3 files · 5.4 MB Repository1 file · 1.8 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00014.safetensors | Weights | 5.0 GB | 5d581901ab0b | | model-00002-of-00014.safetensors | Weights | 5.0 GB | dcdd90d11b4c | | model-00003-of-00014.safetensors | Weights | 5.0 GB | 49246408a50e | | model-00004-of-00014.safetensors | Weights | 5.0 GB | aecdc70918de | | model-00005-of-00014.safetensors | Weights | 5.0 GB | 44e5dd33a77b | | model-00006-of-00014.safetensors | Weights | 5.0 GB | 1d6a9fd17766 | | model-00007-of-00014.safetensors | Weights | 5.0 GB | ff461ecee67c | | model-00008-of-00014.safetensors | Weights | 5.0 GB | d6c0d75ddb64 | | model-00009-of-00014.safetensors | Weights | 5.0 GB | 0e226f745aff | | model-00010-of-00014.safetensors | Weights | 5.0 GB | 2749ba0066b1 | | model-00011-of-00014.safetensors | Weights | 5.0 GB | 8a977a5af1fb | | model-00012-of-00014.safetensors | Weights | 5.0 GB | 0a50fbe2c20e | | model-00013-of-00014.safetensors | Weights | 3.2 GB | ca42cb3b2a73 | | model-00014-of-00014.safetensors | Weights | 2.7 GB | 80c9e147d868 | | config.json | Configuration | 2.4 KB | — | | generation_config.json | Configuration | 210 B | — | | merge-provenance.json | Configuration | 2.8 KB | — | | model.safetensors.index.json | Configuration | 638.3 KB | — | | special_tokens_map.json | Configuration | 563 B | — | | ultra_v3_reasoning_parser.py | Configuration | 1.9 KB | — | | README.md | Documentation | 6.5 KB | — | | Fastino-Nemotron-Finance-HF-Banner.png | Other | 656.5 KB | f73803a865c6 | | chat_template.jinja | Other | 10.2 KB | — | | hf-card-finance-v2.png | Other | 4.7 MB | 886f5ba6b632 | | .gitattributes | Repository | 1.8 KB | — | | tokenizer.json | Tokenizer | 17.1 MB | 623c34567aeb | | tokenizer_config.json | Tokenizer | 177.2 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 65.8 GB [Download from Fastino](https://huggingface.co/fastino/Fastino-Nemotron-3.5-Lightning-Finance) Released by Fastino through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by arXiv:2604.09791 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 65.8 GB | | 16-bit | 63.2 GB | | 8-bit | 31.6 GB | | 4-bit | 15.8 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Compare Fastino-Nemotron-3.5-Lightning-Finance - [Fastino-Nemotron-3.5-Lightning-Finance vs OTel-2.0-LLM-31B-IT](https://savrn.com/models/compare/fastino-nemotron-3-5-lightning-finance-vs-otel-2-0-llm-31b-it) ## Questions About Fastino-Nemotron-3.5-Lightning-Finance ### How much GPU memory does Fastino-Nemotron-3.5-Lightning-Finance need? About 75.8 GB at 16-bit and 18.9 GB at 4-bit: the weights (31.6B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Fastino-Nemotron-3.5-Lightning-Finance on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use Fastino-Nemotron-3.5-Lightning-Finance commercially? Yes. Fastino-Nemotron-3.5-Lightning-Finance is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is Fastino-Nemotron-3.5-Lightning-Finance's context length? 262,144 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [NVIDIA-Nemotron-3-Nano-30B-A3B-BF16](https://savrn.com/models/nvidia-nemotron-3-nano-30b-a3b-bf16) [NVIDIA](https://savrn.com/model-publishers/nvidia) September 2025 \- December 2025 The post-training data has a cutoff date of November 28, 2025\. The pre-training data has a cutoff date of June 25, 2025\. Nemotron-3-Nano-30B-A3B-BF16 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be configured through a flag in the chat template. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in… Open weights other 31.6B parameters 262,144 tokens transformers [View model](https://savrn.com/models/nvidia-nemotron-3-nano-30b-a3b-bf16) Model · Text generation ### [nemotron-30b-a3b-gptq-component-jang-g64-lora-mtp](https://savrn.com/models/nemotron-30b-a3b-gptq-component-jang-g64-lora-mtp) [Roman Romenskyi](https://savrn.com/model-publishers/roman220220) Open weights 31.6B parameters 262,144 tokens mlx [View model](https://savrn.com/models/nemotron-30b-a3b-gptq-component-jang-g64-lora-mtp) Model · Text generation ### [OTel-2.0-LLM-31B-IT](https://savrn.com/models/otel-2-0-llm-31b-it) [Farbod Tavakkoli](https://savrn.com/model-publishers/farbodtavakkoli) OTel-2.0-LLM-31B-IT is a telecom-specialized instruction model post-trained from Gemma 4 31B-IT on approximately 440 billion telecom training tokens. It is the first release in the OTel 2.0 family and is designed to support telco-grade AI workflows across network operations, standards interpretation, product development, network configuration assistance, RAG, and telecom-specific question answering. OTel 2.0 extends the original OTel effort from a RAG-oriented telecom fine-tuning release into a larger domain-adapted training program. The model was trained from a much larger standards and telecom corpus, with new data preparation coverage for direct telecom QnA, abstention, RAG… Open weights apache-2.0 31.3B parameters 262,144 tokens transformers [View model](https://savrn.com/models/otel-2-0-llm-31b-it) Model · Text generation ### [Gemma-4-Writers-31B](https://savrn.com/models/gemma-4-writers-31b) [Ateron](https://savrn.com/model-publishers/ateron) "Less Gemma - more human" I had a lot of fresh and creative experience with both ConicCat tunes, but they had some instability issues, that I hopefully fixed there. Open weights apache-2.0 31.3B parameters 262,144 tokens [View model](https://savrn.com/models/gemma-4-writers-31b) Model · Text generation ### [Wicked-Tutu-31B-Final](https://savrn.com/models/wicked-tutu-31b-final) [Ready.Art](https://savrn.com/model-publishers/readyart) Open weights apache-2.0 31.3B parameters [View model](https://savrn.com/models/wicked-tutu-31b-final) Model · Text generation ### [GLM-4.7-Flash](https://savrn.com/models/glm-4-7-flash) [Z.ai](https://savrn.com/model-publishers/zai-org) Join our Discord community. Check out the GLM-4.7 technical blog, technical report(GLM-4.5). Use GLM-4.7-Flash API services on Z.ai API Platform. One click to GLM-4.7. GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency. Default Settings (Most Tasks) For multi-turn agentic tasks (τ²-Bench and Terminal Bench 2), please turn on Preserved Thinking mode. Terminal Bench, SWE Bench Verified τ^2-Bench For τ^2-Bench evaluation, we added an additional prompt to the Retail and Telecom user interaction to avoid failure modes caused by users ending the interaction… Open weights mit 31.2B parameters 202,752 tokens transformers [View model](https://savrn.com/models/glm-4-7-flash) ## Fastino [All models and datasets](https://savrn.com/model-publishers/fastino) ## Versions - [157ebab9a11f](https://savrn.com/models/fastino-nemotron-3-5-lightning-finance/versions/157ebab9a11f) · current 2026-09-18 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-21. - [Hugging Face record](https://huggingface.co/fastino/Fastino-Nemotron-3.5-Lightning-Finance) - [How the hub is built](https://savrn.com/model-hub/methodology)