NE

Ternary Nemotron 3.5 Lightning 30B A3B

NemotronGGUF by boro64Updated 2026-10-23
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant9.5 GB
Quick answer

Ternary Nemotron 3.5 Lightning 30B A3B needs about 17.0 GB of memory at its main file (a 9.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

Ternary Nemotron 3.5 Lightning 30B A3B – 1.58‑bit MoE model in GGUF

Ternary Nemotron 3.5 Lightning 30B A3B is a 31.6B parameter MoE model with 3B active parameters. It is quantized to ternary weights and packaged as a single GGUF file. The model supports reasoning and tool usage.

Good at

  • Long‑context comprehension
  • Reading and summarisation
  • Retrieval tasks

Limits

  • No vision support
  • Requires 12 GB GPU for 368K context
  • License is other

Best for

  • Chatting with long documents
  • Generating summaries of large texts
  • Retrieval‑augmented queries

Who it’s for. Developers needing a large‑context LLM on consumer GPUs. Researchers interested in MoE behaviour with ternary quantisation. Users of llama.cpp or compatible engines who want a 12 GB GPU deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—9.5 GB 17.0 GB
Too big Get file →

The only available quant is unknown, stored in a 9.47 GB file. It requires about 17 GB of VRAM at 8 k context. For 12 GB GPUs, use the 368K context setting. No other quants are available.

What GPU do you need for Ternary Nemotron 3.5 Lightning 30B A3B?

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 the main file (9.5 GB file, about 17.0 GB in use).

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters31.6B (approximate, mixture of experts)
Active parameters3B
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized byboro64
FamilyNemotron
Licenseother
Downloads (HF)1,163
Last updated2026-10-23

Frequently asked questions about Ternary Nemotron 3.5 Lightning 30B A3B

How much VRAM does Ternary Nemotron 3.5 Lightning 30B A3B need?

About 17.0 GB at its main file with an 8K context window. That is the 9.5 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 Ternary Nemotron 3.5 Lightning 30B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ternary Nemotron 3.5 Lightning 30B A3B GGUF?

It depends on the quant: file is 9.5 GB.

What context length does Ternary Nemotron 3.5 Lightning 30B A3B support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 27.9 GB at 32K.

Where can I download Ternary Nemotron 3.5 Lightning 30B A3B GGUF?

The files are on Hugging Face in the boro64/Ternary-Nemotron-3.5-Lightning-30B-A3B-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 Ternary Nemotron 3.5 Lightning 30B A3B 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 about 17 GB of VRAM at 8 k context. It is designed for 12 GB GPUs with 368K context.

Does this model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is released under an other license, same as the base model.

Similar models

Browse all →

More Nemotron models

All Nemotron →

Other medium models

All medium models →