NE

NVIDIA Nemotron 3.5 Bolt 74B A9B

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

NVIDIA Nemotron 3.5 Bolt 74B A9B needs about 29.3 GB of memory at Q2_K_XL (a 28.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 14 quants, from 1.0 GB to 148.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.2 GB.

NVIDIA Nemotron 3.5 Bolt 74B A9B – a vision‑language model for local agentic tasks

NVIDIA Nemotron 3.5 Bolt 74B A9B is a 81 billion‑parameter vision‑language model designed for local inference. It supports 262,144‑token context and is available in multiple GGUF quantizations. The model is intended for customization and post‑training rather than direct production use.

Good at

  • Vision‑language reasoning
  • Large context handling
  • Customizable via fine‑tuning

Limits

  • Requires 24 GB+ VRAM for 24 GB version
  • No native vision support in lower quants
  • License governed by OpenMDW 1.1

Best for

  • Fine‑tuning for domain‑specific agents
  • Research on vision‑language models
  • Post‑training with custom datasets

Who it’s for. Developers and researchers who need a high‑capacity vision‑language model for local deployment and want to fine‑tune or post‑train on their own data. The model is suitable for commercial or non‑commercial use under the OpenMDW license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.0 GB 1.5 GB
Fits Get file →
IQ1_S18.5 GB 19.0 GB
Too big Get file →
IQ1_M20.3 GB 20.8 GB
Too big Get file →
IQ2_XXS22.0 GB 22.6 GB
Too big Get file →
IQ2_XXS22.0 GB 22.6 GB
Too big Get file →
IQ2_M24.6 GB 25.1 GB
Too big Get file →
Q2_K_XL28.8 GB 29.3 GB
Too big Get file →
IQ3_XXS31.6 GB 32.1 GB
Too big Get file →
Q3_K_XL39.0 GB 39.6 GB
Too big Get file →
Q4_K_XL50.2 GB (3 parts) 50.8 GB
Too big Get file →
Q5_K_XL58.9 GB (3 parts) 59.5 GB
Too big Get file →
Q6_K_XL72.4 GB (3 parts) 72.9 GB
Too big Get file →
Q8_078.9 GB (3 parts) 79.4 GB
Too big Get file →
BF16148.2 GB (4 parts) 148.8 GB
Too big Get file →

For 24 GB VRAM, use the IQ2_XXS or Q4_K_XL quant, which are 22 GB and 50 GB respectively; the IQ2_XXS is the smallest that retains vision support. For 8 GB VRAM, the IQ1_S quant (18.5 GB) is the smallest available, but it may lack full vision capabilities. Larger VRAM allows use of Q4_K_XL or Q5_K_XL for better accuracy.

What GPU do you need for NVIDIA Nemotron 3.5 Bolt 74B A9B?

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 IQ2_XXS (22.0 GB file, about 22.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q2_K_XL (28.8 GB file, about 29.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q3_K_XL (39.0 GB file, about 39.6 GB in use).

Which NVIDIA Nemotron 3.5 Bolt 74B A9B quant should you choose?

Q2_K_XL (28.8 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 the first one in the table at 1.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byunsloth
FamilyNemotron
Licenseother
Downloads (HF)59,791
Last updated2026-10-16

Frequently asked questions about NVIDIA Nemotron 3.5 Bolt 74B A9B

How much VRAM does NVIDIA Nemotron 3.5 Bolt 74B A9B need?

About 29.3 GB at Q2_K_XL with an 8K context window. That is the 28.8 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 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 NVIDIA Nemotron 3.5 Bolt 74B A9B GGUF?

It depends on the quant: file is 1.0 GB, IQ1_S is 18.5 GB, IQ1_M is 20.3 GB, IQ2_XXS is 22.0 GB, IQ2_XXS is 22.0 GB, IQ2_M is 24.6 GB and 8 more.

What context length does NVIDIA Nemotron 3.5 Bolt 74B A9B 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 NVIDIA Nemotron 3.5 Bolt 74B A9B GGUF?

The files are on Hugging Face in the unsloth/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-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 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 the 24 GB version on a 24 GB GPU?

Yes, the 24 GB version is designed to fit in 24 GB of VRAM and run alongside other applications.

Does the model support vision tasks in all quantizations?

Only the quantizations that include vision support are listed; lower quants may lack full vision capability.

What is the context length of this model?

The model supports up to 262,144 tokens of context.

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

Similar models

Browse all →

More from unsloth

All by unsloth →

More Nemotron models

All Nemotron →

Other large models

All large models →