Fastino Nemotron 3.5 Lightning Finance needs about 33.0 GB of memory at Q4_K_M (a 25.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 18.7 GB (Q2_K) to 35.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 28.5 GB.
Fastino Nemotron 3.5 Lightning Finance – 32.9B parameter Mixture‑of‑Experts model for financial reasoning
Fastino Nemotron 3.5 Lightning Finance is a 32.9B‑parameter, 3B‑active mixture‑of‑experts model fine‑tuned for financial document reasoning, numeric question answering, and entity extraction. It is built on the Nemotron 3.5 Lightning architecture and released under Apache 2.0.
Good at
- Financial document reasoning
- Numeric question answering over filings
- Source‑grounded financial research
Limits
- Requires large GPU memory (≈42 GB for Q8_0 at 8K context)
- No vision modalities
- Mixture‑of‑Experts limits single‑GPU inference
Best for
- Financial analysts needing precise extraction
- Researchers building finance‑specific datasets
- Developers integrating finance reasoning into chatbots
Who it’s for. The model is intended for professionals and researchers working with financial texts, tables, and filings who need accurate reasoning and extraction. It is suitable for developers who can provide the necessary GPU resources and are comfortable with llama.cpp or LM Studio workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 18.7 GB | 26.3 GB | Too big | Get file → | |
| IQ3_S | 18.7 GB | 26.3 GB | Too big | Get file → | |
| IQ3_XS | 18.7 GB | 26.3 GB | Too big | Get file → | |
| Q3_K_S | 18.7 GB | 26.3 GB | Too big | Get file → | |
| IQ4_XS | 18.7 GB | 26.3 GB | Too big | Get file → | |
| IQ4_NL | 18.7 GB | 26.3 GB | Too big | Get file → | |
| Q4_0 | 18.8 GB | 26.4 GB | Too big | Get file → | |
| IQ3_M | 18.9 GB | 26.5 GB | Too big | Get file → | |
| Q2_K_XL | 19.0 GB | 26.6 GB | Too big | Get file → | |
| Q3_K_M | 20.7 GB | 28.3 GB | Too big | Get file → | |
| Q3_K_XL | 21.0 GB | 28.6 GB | Too big | Get file → | |
| Q3_K_L | 21.6 GB | 29.2 GB | Too big | Get file → | |
| Q4_K_S | 22.8 GB | 30.4 GB | Too big | Get file → | |
| Q5_K_S | 24.8 GB | 32.4 GB | Too big | Get file → | |
| Q4_K_M | 25.4 GB | 33.0 GB | Too big | Get file → | |
| Q4_K_XL | 25.8 GB | 33.4 GB | Too big | Get file → | |
| Q5_K_M | 27.0 GB | 34.7 GB | Too big | Get file → | |
| Q5_K_XL | 27.4 GB | 35.0 GB | Too big | Get file → | |
| Q6_K | 34.9 GB | 42.5 GB | Too big | Get file → | |
| Q8_0 | 35.0 GB | 42.6 GB | Too big | Get file → | |
| Q6_K_XL | 35.3 GB | 42.9 GB | Too big | Get file → | |
| Q8_0 | 35.3 GB | 42.9 GB | Too big | Get file → |
For a GPU with 12 GB VRAM, the Q2_K or IQ3_S quantizations (file size 18.66 GB, estimated 26.3 GB at 8K context) are the most feasible. If you have 16 GB VRAM, consider Q4_0 (file size 18.81 GB, 26.4 GB estimate). For larger GPUs (≥32 GB), higher‑quality quants such as Q4_K_M (file size 25.43 GB, 33 GB estimate) or Q5_K_S (file size 24.81 GB, 32.4 GB estimate) provide better accuracy.
What GPU do you need for Fastino Nemotron 3.5 Lightning Finance?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_S (22.8 GB file, about 30.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.3 GB file, about 42.9 GB in use).
Which Fastino Nemotron 3.5 Lightning Finance quant should you choose?
Q4_K_M is the usual starting point for Fastino Nemotron 3.5 Lightning Finance: it balances file size and quality well. Here it is a 25.4 GB file.
The Q8_0 file is 35.0 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 18.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Fastino Nemotron 3.5 Lightning Finance
How much VRAM does Fastino Nemotron 3.5 Lightning Finance need?
About 33.0 GB at Q4_K_M with an 8K context window. That is the 25.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Fastino Nemotron 3.5 Lightning Finance on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Fastino Nemotron 3.5 Lightning Finance GGUF?
It depends on the quant: Q2_K is 18.7 GB, IQ3_S is 18.7 GB, IQ3_XS is 18.7 GB, Q3_K_S is 18.7 GB, IQ4_XS is 18.7 GB, IQ4_NL is 18.7 GB and 16 more.
What context length does Fastino Nemotron 3.5 Lightning Finance support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.1 GB at 8K and 28.5 GB at 32K.
Where can I download Fastino Nemotron 3.5 Lightning Finance GGUF?
The files are on Hugging Face in the nicolasembleton/Fastino-Nemotron-3.5-Lightning-Finance-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Fastino Nemotron 3.5 Lightning Finance use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Fastino Nemotron 3.5 Lightning Finance on 8 GB VRAM?
No. The smallest quant requires at least 26.3 GB of VRAM at 8K context, so 8 GB is insufficient.
Does the model support image inputs?
No. The model is text‑only and has no vision modalities.
What license applies to the GGUF weights?
The GGUF weights are released under Apache 2.0, the same license as the original checkpoint.