Hermes3.6 35B A3B Uncensored Genesis NVFP4 needs about 22.6 GB of memory at its main file (a 21.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 21.5 GB to 22.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Hermes3.6 35B A3B Uncensored Genesis NVFP4 – a 35B Qwen model with MoE
Hermes3.6 35B A3B Uncensored Genesis NVFP4 is a 35B parameter Qwen model with 3B active parameters per forward pass. It supports reasoning, tools, and vision. The model is released under the apache-2.0 license.
Good at
- Reasoning tasks
- Tool usage
- Vision integration
Limits
- No vision support in some runtimes
- Large VRAM requirement
- Requires GGUF format
Best for
- Complex reasoning workflows
- Tool‑augmented applications
- Vision‑enabled inference
Who it’s for. Developers building advanced LLM applications that need a large, mixture‑of‑experts model with reasoning, tool, and vision capabilities. The model is suitable for users with sufficient GPU memory and a GGUF‑compatible runtime.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 21.5 GB | 22.6 GB | Too big | Get file → | |
| — | 21.5 GB | 22.6 GB | Too big | Get file → | |
| — | 21.5 GB | 22.6 GB | Too big | Get file → | |
| — | 22.2 GB | 23.3 GB | Too big | Get file → |
All available GGUF files are unquantized and have a file size of 21.47 GB or 22.17 GB. The estimated VRAM usage at an 8 k context is 22.6 GB or 23.3 GB. These estimates are approximate. If you have 24 GB or more VRAM, any of the files will run. For lower budgets, a smaller quant is required but not provided here.
What GPU do you need for Hermes3.6 35B A3B Uncensored Genesis NVFP4?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (22.2 GB file, about 23.3 GB in use).
Which Hermes3.6 35B A3B Uncensored Genesis NVFP4 quant should you choose?
If memory is tight, the smallest file is the first one in the table at 21.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Hermes3.6 35B A3B Uncensored Genesis NVFP4
How much VRAM does Hermes3.6 35B A3B Uncensored Genesis NVFP4 need?
About 22.6 GB at its main file with an 8K context window. That is the 21.5 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 Hermes3.6 35B A3B Uncensored Genesis NVFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Hermes3.6 35B A3B Uncensored Genesis NVFP4 GGUF?
It depends on the quant: file is 21.5 GB, file is 21.5 GB, file is 21.5 GB, file is 22.2 GB.
What context length does Hermes3.6 35B A3B Uncensored Genesis NVFP4 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download Hermes3.6 35B A3B Uncensored Genesis NVFP4 GGUF?
The files are on Hugging Face in the jan1k/Hermes3.6-35B-A3B-Uncensored-Genesis-NVFP4-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 Hermes3.6 35B A3B Uncensored Genesis NVFP4 use?
Hugging Face lists the license as apache-2.0. 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 Hermes3.6 on 8 GB VRAM?
No. The model requires at least 22.6 GB VRAM at an 8 k context, so 8 GB is insufficient.
Does the model support vision?
Yes, the model detects vision capability, but some runtimes may not support it due to the NVFP4 format.
What license applies to this model?
The model is licensed under apache-2.0.