Nemotron-3.5-Bolt-E4B-Heretic needs about 7.7 GB of memory at Q5_K_XL (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 3.7 GB (Q2_K_XL) to 14.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
7.46B parameter Nemotron-3.5-Bolt-E4B-Heretic in GGUF format
Nemotron-3.5-Bolt-E4B-Heretic is a 7.46B parameter model based on Gemma4 architecture. It supports reasoning, tools, and vision. The model is available in multiple GGUF quantizations ranging from Q2_K_XL to BF16.
Good at
- Reasoning and instruction following
- Tool use and multi‑turn dialogue
- Vision tasks
Limits
- No vision support in quantized versions
- Large VRAM requirement for higher precision
- License is other, not open source
Best for
- Local voice assistants
- Interactive personas
- Embedded AI agents
Who it’s for. Developers building low‑latency local assistants who need a compact model with strong conversational and vision capabilities. The model is suitable for commercial or non‑commercial use under its license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_XL | 3.7 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_XL | 4.2 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_XL | 5.0 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_XL | 5.8 GB | 7.7 GB | Tight | Get file → | |
| Q6_K_XL | 7.2 GB | 9.1 GB | Too big | Get file → | |
| Q8_0 | 8.0 GB | 9.9 GB | Too big | Get file → | |
| Q8_K_XL | 8.1 GB | 10.0 GB | Too big | Get file → | |
| BF16 | 14.9 GB | 16.9 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_XL (est. 6.9 GB) or Q5_K_XL (est. 7.7 GB). For 16 GB VRAM use Q8_0 (est. 9.9 GB) or Q8_K_XL (est. 10 GB). BF16 requires 16.9 GB and is best for maximum quality.
What GPU do you need for Nemotron-3.5-Bolt-E4B-Heretic?
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 Q2_K_XL (3.7 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_XL (5.8 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_K_XL (8.1 GB file, about 10.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_K_XL (8.1 GB file, about 10.0 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (14.9 GB file, about 16.9 GB in use).
Which Nemotron-3.5-Bolt-E4B-Heretic quant should you choose?
Q5_K_XL (5.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q2_K_XL at 3.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nemotron-3.5-Bolt-E4B-Heretic
How much VRAM does Nemotron-3.5-Bolt-E4B-Heretic need?
About 7.7 GB at Q5_K_XL with an 8K context window. That is the 5.8 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-Heretic on an 8 GB GPU?
Yes, with Q5_K_XL: the 5.8 GB file needs about 7.7 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-Heretic GGUF?
It depends on the quant: Q2_K_XL is 3.7 GB, Q3_K_XL is 4.2 GB, Q4_K_XL is 5.0 GB, Q5_K_XL is 5.8 GB, Q6_K_XL is 7.2 GB, Q8_0 is 8.0 GB and 2 more.
What context length does Nemotron-3.5-Bolt-E4B-Heretic 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 Nemotron-3.5-Bolt-E4B-Heretic GGUF?
The files are on Hugging Face in the grumd0/Nemotron-3.5-Bolt-E4B-Heretic-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-Heretic 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 Q4_K_XL on 8 GB VRAM?
Yes, Q4_K_XL uses about 6.9 GB of VRAM at 8 k context, which fits in 8 GB.
Does the model support vision?
The base model has vision capability, but quantized GGUF files do not include vision support.
Is the model free to use?
The model is released under an other license, allowing commercial or non‑commercial use but not open source.