NE

Nemotron 3.5 Bolt E4B GSQ RCO

NemotronGGUF by abenzerpsUpdated 2026-10-25
Download on Hugging Face
Parameters7.52B
Context128K
Layers5
Architecturedflash
Smallest quant0.4 GB
Quick answer

Nemotron 3.5 Bolt E4B GSQ RCO needs about 4.6 GB of memory at IQ3_M (a 4.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 0.4 GB (Q8_0) to 5.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.

Nemotron 3.5 Bolt E4B GSQ RCO – 7.52B parameter SLM with 131072 token context

Nemotron 3.5 Bolt E4B GSQ RCO is a small language model derived from NVIDIA‑Nemotron‑3.5‑Bolt‑E4B‑BF16. It supports reasoning and tool use and is optimized for local inference with DFlash speculative decoding. The model is available under the OpenMDW‑1.1 license.

Good at

  • Reasoning
  • Tool use
  • Low‑memory inference

Limits

  • No vision support
  • Requires BF16 or higher for best performance
  • License is OpenMDW‑1.1

Best for

  • Local voice assistants
  • Interactive personas
  • Embedded edge interfaces

Who it’s for. Developers building low‑latency, low‑memory AI agents that need strong conversational and tool‑use capabilities. The model is suitable for commercial or non‑commercial use under the OpenMDW‑1.1 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.4 GB 1.1 GB
Fits Get file →
BF160.7 GB 1.4 GB
Fits Get file →
IQ3_M4.0 GB 4.6 GB
Fits Get file →
IQ4_XS4.8 GB 5.5 GB
Fits Get file →
Q5_K_M5.9 GB 6.5 GB
Fits Get file →

For 8 GB VRAM, use Q8_0 (0.4 GB file, 1.1 GB memory at 8k context). For 4 GB VRAM, use IQ4_XS (4.8 GB file, 5.5 GB memory). For 16 GB VRAM, BF16 (0.74 GB file, 1.4 GB memory) or Q5_K_M (5.87 GB file, 6.5 GB memory). Estimates are approximate.

What GPU do you need for Nemotron 3.5 Bolt E4B GSQ RCO?

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 BF16 (0.7 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.8 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 6.5 GB in use).

Which Nemotron 3.5 Bolt E4B GSQ RCO quant should you choose?

IQ3_M (4.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is Q8_0 at 0.4 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters7.52B
Layers5
Trained context131,072 tokens
KV cache (fp16)20 KB per token

Source

Quantized byabenzerps
FamilyNemotron
Licenseother
Downloads (HF)6,052
Last updated2026-10-25

Frequently asked questions about Nemotron 3.5 Bolt E4B GSQ RCO

How much VRAM does Nemotron 3.5 Bolt E4B GSQ RCO need?

About 4.6 GB at IQ3_M with an 8K context window. That is the 4.0 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 E4B GSQ RCO on an 8 GB GPU?

Yes, with Q5_K_M: the 5.9 GB file needs about 6.5 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 E4B GSQ RCO GGUF?

It depends on the quant: Q8_0 is 0.4 GB, BF16 is 0.7 GB, IQ3_M is 4.0 GB, IQ4_XS is 4.8 GB, Q5_K_M is 5.9 GB.

What context length does Nemotron 3.5 Bolt E4B GSQ RCO support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.7 GB at 32K.

Where can I download Nemotron 3.5 Bolt E4B GSQ RCO GGUF?

The files are on Hugging Face in the abenzerps/Nemotron-3.5-Bolt-E4B-GSQ-RCO-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 GSQ RCO 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 E4B GSQ RCO on 8 GB VRAM?

Yes, the Q8_0 quantization uses 1.1 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license governs the model?

The model is distributed under the OpenMDW‑1.1 license, matching the upstream NVIDIA model.

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

Similar models

Browse all →

More from abenzerps

All by abenzerps →

More Nemotron models

All Nemotron →

Other small models

All small models →