NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB needs about 34.3 GB of memory at its main file (a 22.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 47.2 GB.
NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB – a vision‑language MoE model in GGUF format
NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB is a 74‑billion‑parameter vision‑language model. The GGUF file is 22.02 GB and requires about 34.3 GB of VRAM at 8 k context. It is intended for customization and post‑training rather than direct production inference.
Good at
- Vision‑language tasks
- Customizable via post‑training
- Efficient 2‑bit quantization
Limits
- Requires 8 k context or higher
- Large VRAM requirement (≈34.3 GB)
- No explicit license beyond OpenMDW 1.1
Best for
- Fine‑tuning for domain‑specific agents
- Research evaluation of MoE models
- Deploying on high‑end local GPUs
Who it’s for. Developers and researchers who need a multimodal model with large context and are able to run it on GPUs with at least 34 GB of VRAM. The model is suitable for post‑training workflows and custom quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 22.0 GB | 34.3 GB | Too big | Get file → |
The only available GGUF quant is the 22.02 GB file. It requires about 34.3 GB of VRAM at 8 k context. For lower memory budgets, consider creating a custom quantized variant, but the current release does not provide one.
What GPU do you need for NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB?
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: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is the main file (22.0 GB file, about 34.3 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB
How much VRAM does NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB need?
About 34.3 GB at its main file with an 8K context window. That is the 22.0 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 Abliterated 24GB on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 34.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB GGUF?
It depends on the quant: file is 22.0 GB.
What context length does NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB 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 Abliterated 24GB GGUF?
The files are on Hugging Face in the BoldingBuilds/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-Abliterated-24GB-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 NVIDIA Nemotron 3.5 Bolt 74B A9B Abliterated 24GB 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 model requires approximately 34.3 GB of VRAM at 8 k context, far exceeding 8 GB.
Does this model support vision tasks?
Yes. The model is a vision‑language model and includes a projector for multimodal input.
Is the model free to use?
The model is released under the OpenMDW License Agreement v1.1, allowing commercial or non‑commercial use.