NE

Nemotron 3.5 Bolt 74B A9B CRACK 24GB

NemotronGGUF by dealignaiUpdated 2026-10-16
Download on Hugging Face
Parameters74B
Context256K
Layers5
Architecturedflash
Smallest quant1.0 GB
Quick answer

Nemotron 3.5 Bolt 74B A9B CRACK 24GB needs about 1.5 GB of memory at its main file (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.0 GB to 22.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.2 GB.

Nemotron 3.5 Bolt 74B A9B CRACK 24GB – a 74B vision‑language model quantized for 24GB VRAM

Nemotron 3.5 Bolt 74B A9B is a vision‑language model with 74B parameters and a 262144 token context. The CRACK 24GB GGUF version uses a native 2‑bit quantization to fit in 24GB of memory. It is intended for customization, post‑training, and research use.

Good at

  • Vision‑language tasks
  • Customizable post‑training
  • Research evaluation

Limits

  • Requires 24GB VRAM for full model
  • No direct production inference support
  • License governed by OpenMDW 1.1

Best for

  • Local agentic task execution
  • Fine‑tuning on proprietary data
  • Latency‑optimized inference with llama.cpp or vLLM

Who it’s for. Developers and researchers who need a large vision‑language model that can be fine‑tuned locally and run within a 24GB VRAM budget. The model is suitable for post‑training, domain adaptation, and creating quantized variants for deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.0 GB 1.5 GB
Fits Get file →
—22.0 GB 22.6 GB
Too big Get file →

For a 24GB VRAM budget, use the 22.02 GB GGUF file (est. 22.6 GB memory at 8K context). If a smaller file is needed, the 1 GB GGUF file (est. 1.5 GB memory) can be used but will lack full model capacity.

What GPU do you need for Nemotron 3.5 Bolt 74B A9B CRACK 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: the best quant that fits is the main file (1.0 GB file, about 1.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 1.5 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 1.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 1.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (1.0 GB file, about 1.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (22.0 GB file, about 22.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters74B
Layers5
Trained context262,144 tokens
KV cache (fp16)5 KB per token

Source

Quantized bydealignai
FamilyNemotron
Licenseother
Downloads (HF)3,502
Last updated2026-10-16

Frequently asked questions about Nemotron 3.5 Bolt 74B A9B CRACK 24GB

How much VRAM does Nemotron 3.5 Bolt 74B A9B CRACK 24GB need?

About 1.5 GB at its main file with an 8K context window. That is the 1.0 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 Nemotron 3.5 Bolt 74B A9B CRACK 24GB on an 8 GB GPU?

Yes, with the smaller files: the 1.0 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nemotron 3.5 Bolt 74B A9B CRACK 24GB GGUF?

It depends on the quant: file is 1.0 GB, file is 22.0 GB.

What context length does Nemotron 3.5 Bolt 74B A9B CRACK 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 0.0 GB at 8K and 0.2 GB at 32K.

Where can I download Nemotron 3.5 Bolt 74B A9B CRACK 24GB GGUF?

The files are on Hugging Face in the dealignai/Nemotron-3.5-Bolt-74B-A9B-CRACK-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 Nemotron 3.5 Bolt 74B A9B CRACK 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 Nemotron 3.5 Bolt 74B A9B on 8GB VRAM?

No, the 24GB GGUF file requires at least 24GB VRAM. The 1GB file is too small to provide full model functionality.

Does the model support vision tasks?

Yes, the model includes a vision tower and is marked as vision capable.

Is the model safe for end‑user deployment?

The model contains alignment work and should not be deployed to end users without separate downstream safety controls.

Other GGUFs of NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16

Similar models

Browse all →

More from dealignai

All by dealignai →

More Nemotron models

All Nemotron →

Other large models

All large models →