NVIDIA Nemotron 3.5 Bolt E4B DFlash needs about 1.4 GB of memory at its main file (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 DFlash – a draft model for speculative decoding
NVIDIA Nemotron 3.5 Bolt E4B DFlash is a draft model designed for speculative decoding with the DFlash architecture. It contains 0.36 billion parameters and supports a context length of 131072 tokens. The model is provided in a single GGUF file.
Good at
- reasoning
- tools
- speculative decoding
Limits
- no vision support
- no license info
- requires llama.cpp 2.63.0+
Best for
- LLM inference with speculative decoding
- research on draft token generation
- testing DFlash on DGX Spark
Who it’s for. Developers and researchers who want to experiment with NVIDIA’s draft token generation approach. The model is suitable for those using LM Studio and llama.cpp for advanced inference techniques.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.7 GB | 1.4 GB | Fits | Get file → |
The only available quant is unknown, file size 0.74 GB. It requires about 1.4 GB of memory at 8 k context. For 8 GB VRAM, this model fits comfortably. For 4 GB VRAM, it may be too large.
What GPU do you need for NVIDIA Nemotron 3.5 Bolt E4B 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 the main file (0.7 GB file, about 1.4 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about NVIDIA Nemotron 3.5 Bolt E4B DFlash
How much VRAM does NVIDIA Nemotron 3.5 Bolt E4B DFlash need?
About 1.4 GB at its main file 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 DFlash on an 8 GB GPU?
Yes, with the smaller files: 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 DFlash GGUF?
It depends on the quant: file is 0.7 GB.
What context length does NVIDIA Nemotron 3.5 Bolt E4B 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 DFlash GGUF?
The files are on Hugging Face in the lmstudio-community/NVIDIA-Nemotron-3.5-Bolt-E4B-DFlash-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, the model requires approximately 1.4 GB of memory at 8 k context, so it fits within 8 GB VRAM.
Does this model support vision tasks?
No, the model does not include vision capabilities.
What engine version is needed?
It requires llama.cpp engine 2.63.0 or newer.