NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard needs about 31.2 GB of memory at IQ2_XXS (a 18.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 17.9 GB (IQ2_XXS) to 21.0 GB (IQ2_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 47.2 GB.
NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard – a 74B vision‑language model in GGUF format
The model is a 74B parameter vision‑language model with 9B active parameters in a mixture of experts architecture. It was trained on 262144 context tokens and is available in four IQ2_XXS quantized rungs. The model is released under an OpenMDW license.
Good at
- reasoning
- tools
- vision
Limits
- no vision support in some runtimes
- requires large VRAM for higher rungs
- license is OpenMDW
Best for
- local agentic tasks
- customization and post‑training
- vision‑language inference
Who it’s for. Developers and researchers who need a large, vision‑language model that can be run locally and customized. The model is suitable for building specialized AI agents and for experimentation with mixture‑of‑experts architectures.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 17.9 GB | 30.2 GB | Too big | Get file → | |
| IQ2_XXS | 18.9 GB | 31.2 GB | Too big | Get file → | |
| IQ2_XXS | 19.9 GB | 32.2 GB | Too big | Get file → | |
| IQ2_XXS | 21.0 GB | 33.3 GB | Too big | Get file → |
For a 24GB VRAM machine, use the 20.98 GB IQ2_XXS file which estimates 33.3 GB memory at 8k context. If you have 21.9 GB VRAM, the 19.93 GB file uses 32.2 GB memory. For 21.0 GB VRAM, the 18.91 GB file uses 31.2 GB memory. The 17.88 GB file uses 30.2 GB memory and is the lightest option.
What GPU do you need for NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard?
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 IQ2_XXS (18.9 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_XXS (21.0 GB file, about 33.3 GB in use).
Which NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard quant should you choose?
IQ2_XXS (18.9 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ2_XXS at 17.9 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
Frequently asked questions about NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard
How much VRAM does NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard need?
About 31.2 GB at IQ2_XXS with an 8K context window. That is the 18.9 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 NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 30.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard GGUF?
It depends on the quant: IQ2_XXS is 17.9 GB, IQ2_XXS is 18.9 GB, IQ2_XXS is 19.9 GB, IQ2_XXS is 21.0 GB.
What context length does NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 11.8 GB at 8K and 47.2 GB at 32K.
Where can I download NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard GGUF?
The files are on Hugging Face in the PollardWeights/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Pollard repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does NVIDIA Nemotron 3.5 Bolt 74B A9B Pollard use?
Hugging Face lists the license as other. 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 this model on 8 GB VRAM?
No, the smallest quant requires at least 30.2 GB memory at 8k context, so 8 GB VRAM is insufficient.
What is the context length supported?
The model was trained on 262144 tokens and supports that context length in inference.
Is the model free to use?
Yes, it is released under the OpenMDW license and can be used for commercial or non‑commercial purposes.