NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash needs about 1.4 GB of memory at BF16 (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash – BF16 GGUF for low‑latency reasoning
The NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash is a BF16 GGUF draft model for speculative decoding. It is intended to be used together with the target Nemotron‑3.5‑Bolt‑E4B‑4GB model on workstation GPUs. The draft model does not contain token embeddings or an output head.
Good at
- Reasoning
- Tool use
- Agentic workflows
Limits
- Requires target Nemotron‑3.5‑Bolt‑E4B‑4GB
- No standalone inference
- Limited to text input
Best for
- Local low‑latency reasoning
- Chat with tool integration
- Agentic task execution
Who it’s for. Developers who run NVIDIA Nemotron models locally with llama.cpp and need faster speculative decoding on workstation GPUs. The model is designed for use alongside the full Nemotron‑3.5‑Bolt‑E4B‑4GB checkpoint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 0.7 GB | 1.4 GB | Fits | Get file → |
The only available quant is BF16, file size 0.74 GB. It requires approximately 1.4 GB of VRAM at 8 k context. For 8 GB VRAM, BF16 is suitable; for lower VRAM budgets, no other quant is available.
What GPU do you need for NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash?
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).
Which NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash quant should you choose?
BF16 (0.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash
How much VRAM does NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash need?
About 1.4 GB at BF16 with an 8K context window. That is the 0.7 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 E4B 4GB DFlash on an 8 GB GPU?
Yes, with BF16: the 0.7 GB file needs about 1.4 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 E4B 4GB DFlash GGUF?
It depends on the quant: BF16 is 0.7 GB.
What context length does NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash 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 NVIDIA Nemotron 3.5 Bolt E4B 4GB DFlash GGUF?
The files are on Hugging Face in the nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-DFlash 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 E4B 4GB DFlash 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?
Yes, BF16 requires about 1.4 GB of VRAM at 8 k context, leaving room for other processes.
Does this model support vision or audio input?
No, the model only supports text input; image and audio support is not included.
Do I need the full Nemotron‑3.5‑Bolt‑E4B‑4GB model?
Yes, the draft model uses the target model’s token embeddings and output head at runtime.