NE

Nemotron 3.5 Bolt E4B NVFP4

NemotronGGUF by WhiskyAKMUpdated 2026-10-24
Download on Hugging Face
Parameters7.52B
Context64K
Layers42
Architecturegemma4
Smallest quant4.3 GB
Quick answer

Nemotron 3.5 Bolt E4B NVFP4 needs about 6.2 GB of memory at its main file (a 4.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.3 GB to 5.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Nemotron 3.5 Bolt E4B NVFP4 – multimodal GGUF model

Nemotron 3.5 Bolt E4B NVFP4 is a multimodal GGUF conversion of NVIDIA’s Nemotron‑3.5‑Bolt‑E4B. It supports text, image, and audio inputs and outputs text. The model is built on the gemma4 architecture with 7.52 billion parameters and a 65 536‑token context window.

Good at

  • Multimodal input handling
  • Efficient on‑device inference
  • Low‑memory deployment

Limits

  • No vision support in the provided GGUF files
  • Requires NVFP4‑compatible inference engines
  • License is openmdw‑1.1

Best for

  • Embedded assistants
  • Edge devices
  • Low‑latency local inference

Who it’s for. Developers building lightweight AI agents that need multimodal capabilities on laptops or mobile devices. The model is suitable for commercial or non‑commercial use under the openmdw‑1.1 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—4.3 GB 6.2 GB
Fits Get file →
—5.2 GB 7.1 GB
Fits Get file →

For 8 GB VRAM use the 4.29 GB file (est. 6.2 GB memory at 8 k context). For 12 GB VRAM use the 5.19 GB file (est. 7.1 GB memory at 8 k context). Memory estimates are approximate.

What GPU do you need for Nemotron 3.5 Bolt E4B NVFP4?

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: the best quant that fits is the main file (5.2 GB file, about 7.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.52B
Layers42
Trained context65,536 tokens
KV cache (fp16)168 KB per token

Source

Quantized byWhiskyAKM
FamilyNemotron
Downloads (HF)749
Last updated2026-10-24

Frequently asked questions about Nemotron 3.5 Bolt E4B NVFP4

How much VRAM does Nemotron 3.5 Bolt E4B NVFP4 need?

About 6.2 GB at its main file with an 8K context window. That is the 4.3 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 E4B NVFP4 on an 8 GB GPU?

Yes, with the smaller files: the 5.2 GB file needs about 7.1 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 E4B NVFP4 GGUF?

It depends on the quant: file is 4.3 GB, file is 5.2 GB.

What context length does Nemotron 3.5 Bolt E4B NVFP4 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Nemotron 3.5 Bolt E4B NVFP4 GGUF?

The files are on Hugging Face in the WhiskyAKM/Nemotron-3.5-Bolt-E4B-NVFP4-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 E4B NVFP4 use?

Hugging Face lists the license as openmdw-1.1. 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?

Yes, the 4.29 GB file requires about 6.2 GB memory at 8 k context, which fits in 8 GB VRAM with headroom.

Does this model support vision?

The GGUF files contain vision and audio encoders, but the provided files are for multimodal use only if the inference engine supports NVFP4.

What license applies?

The model is released under the openmdw‑1.1 license, allowing commercial or non‑commercial use.

Other GGUFs of NVIDIA-Nemotron-3.5-Bolt-E4B-BF16

Similar models

Browse all →

More from WhiskyAKM

All by WhiskyAKM →

More Nemotron models

All Nemotron →

Other small models

All small models →