NE

Nemotron 3.5 Bolt 74B A9B 16GB

NemotronGGUF by anik-jhaUpdated 2026-10-18
Download on Hugging Face
Parameters24.4B
Context256K
Layers88
Architecturenemotron_h_moe
Smallest quant9.1 GB
Quick answer

Nemotron 3.5 Bolt 74B A9B 16GB needs about 21.4 GB of memory at IQ2_XXS (a 9.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 9.1 GB (IQ2_XXS) to 13.4 GB (IQ2_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 47.2 GB.

Nemotron 3.5 Bolt 74B A9B 16GB – a compact vision‑language model for local agents

Nemotron 3.5 Bolt 74B A9B 16GB is a 24.4 billion‑parameter model with 9 billion active experts. It supports coding, reasoning, tool calling and vision tasks. The model is quantized to 2‑bit IQ2_XXS and fits on a 16 GB GPU.

Good at

  • Coding and tool calling
  • Vision‑language reasoning
  • Long‑context handling

Limits

  • Requires 16 GB GPU memory
  • No re‑quantization available
  • License is other

Best for

  • Local agent harnesses
  • Tool‑driven web browsing
  • Terminal‑based coding tasks

Who it’s for. Developers building local AI agents that need coding, vision and tool‑calling capabilities on a single 16 GB GPU. The model is suitable for commercial or non‑commercial use under the OpenMDW License Agreement.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS9.1 GB 21.4 GB
Too big Get file →
IQ2_XXS13.4 GB 25.7 GB
Too big Get file →

For a 16 GB GPU, use the 13.38 GB IQ2_XXS file; it peaks at 25.7 GB memory at 8 k context, which is within the 16 GB limit when accounting for the 1.7 GB vision projector. The 9.06 GB IQ2_XXS file uses 21.4 GB memory at 8 k context and is more memory‑efficient.

What GPU do you need for Nemotron 3.5 Bolt 74B A9B 16GB?

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: the best quant that fits is IQ2_XXS (9.1 GB file, about 21.4 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_XXS (13.4 GB file, about 25.7 GB in use).

Which Nemotron 3.5 Bolt 74B A9B 16GB quant should you choose?

IQ2_XXS (9.1 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters24.4B (approximate, mixture of experts)
Active parameters9B
Layers88
Trained context262,144 tokens
KV cache (fp16)1408 KB per token

Source

Quantized byanik-jha
FamilyNemotron
Licenseother
Downloads (HF)2,041
Last updated2026-10-18

Frequently asked questions about Nemotron 3.5 Bolt 74B A9B 16GB

How much VRAM does Nemotron 3.5 Bolt 74B A9B 16GB need?

About 21.4 GB at IQ2_XXS with an 8K context window. That is the 9.1 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 16GB on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nemotron 3.5 Bolt 74B A9B 16GB GGUF?

It depends on the quant: IQ2_XXS is 9.1 GB, IQ2_XXS is 13.4 GB.

What context length does Nemotron 3.5 Bolt 74B A9B 16GB 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 Nemotron 3.5 Bolt 74B A9B 16GB GGUF?

The files are on Hugging Face in the anik-jha/Nemotron-3.5-Bolt-74B-A9B-16GB-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 16GB 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.

Does this model work with llama.cpp?

Yes, any llama.cpp build that supports NVIDIA's Bolt 24GB GGUF format will run these expert‑pruned files.

Is vision support included?

Yes, the model includes a vision encoder and projector for image and video frames.

Other GGUFs of NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF

Similar models

Browse all →

More from anik-jha

All by anik-jha →

More Nemotron models

All Nemotron →

Other medium models

All medium models →