NVIDIA-Nemotron-3.5-Bolt-E4B needs about 7.0 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.0 GB (IQ3_S) to 8.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
NVIDIA‑Nemotron‑3.5‑Bolt‑E4B – a small reasoning and chat model
NVIDIA‑Nemotron‑3.5‑Bolt‑E4B is a 7.52 billion‑parameter model built from Gemma‑4‑E4B‑it. It supports reasoning, tools, and vision. The model is designed for low‑memory, low‑TTFT operation and can be used for commercial or non‑commercial purposes.
Good at
- Reasoning
- Tool use
- Vision
Limits
- No vision support in quantized versions
- Requires 8 k context for memory estimates
- License governed by OpenMDW 1.1
Best for
- Local voice assistants
- Interactive personas
- Embedded/edge interfaces
Who it’s for. Developers building lightweight AI agents that need fast local inference and low memory usage. The model is suitable for edge deployments and applications requiring quick response times.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 4.0 GB | 5.9 GB | Fits | Get file → | |
| IQ4_XS | 4.5 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_M | 5.1 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_M | 5.5 GB | 7.4 GB | Tight | Get file → | |
| Q6_K | 7.4 GB | 9.3 GB | Too big | Get file → | |
| Q8_0 | 8.0 GB | 9.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.06 GB, estimated 7 GB memory at 8 k context). For 6 GB VRAM, use IQ4_XS (4.48 GB, 6.4 GB memory). For 4 GB VRAM, use IQ3_S (4.03 GB, 5.9 GB memory). Estimates are approximate.
What GPU do you need for NVIDIA-Nemotron-3.5-Bolt-E4B?
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: the best quant that fits is IQ3_S (4.0 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.5 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
Which NVIDIA-Nemotron-3.5-Bolt-E4B quant should you choose?
Q4_K_M is the usual starting point for NVIDIA-Nemotron-3.5-Bolt-E4B: it balances file size and quality well. Here it is a 5.1 GB file.
The Q8_0 file is 8.0 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ3_S at 4.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about NVIDIA-Nemotron-3.5-Bolt-E4B
How much VRAM does NVIDIA-Nemotron-3.5-Bolt-E4B need?
About 7.0 GB at Q4_K_M with an 8K context window. That is the 5.1 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 NVIDIA-Nemotron-3.5-Bolt-E4B on an 8 GB GPU?
Yes, with Q5_K_M: the 5.5 GB file needs about 7.4 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 GGUF?
It depends on the quant: IQ3_S is 4.0 GB, IQ4_XS is 4.5 GB, Q4_K_M is 5.1 GB, Q5_K_M is 5.5 GB, Q6_K is 7.4 GB, Q8_0 is 8.0 GB.
What context length does NVIDIA-Nemotron-3.5-Bolt-E4B support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download NVIDIA-Nemotron-3.5-Bolt-E4B GGUF?
The files are on Hugging Face in the AtomicChat/NVIDIA-Nemotron-3.5-Bolt-E4B-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 NVIDIA-Nemotron-3.5-Bolt-E4B 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 NVIDIA‑Nemotron‑3.5‑Bolt‑E4B on 8 GB VRAM?
Yes, the Q4_K_M quantized version uses about 7 GB memory at 8 k context, fitting within 8 GB VRAM.
Does the model support vision?
The base model has vision capability, but quantized files listed do not include vision support.
What license applies to this model?
Use is governed by the OpenMDW License Agreement, version 1.1, with Google Gemma 4 governed by Apache 2.0.