nicoboss.Hermes 3 Llama 3.1 405B Uncensored needs about 200.1 GB of memory at Q3_K_M (a 195.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 149.3 GB (Q2_K) to 431.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 16.9 GB.
nicoboss.Hermes 3 Llama 3.1 405B Uncensored is a 406B-parameter Llama model in GGUF format, quantized by llmtraining-scraper. Its trained context length is 128K tokens. The repository has 3 quant files, from 149.3 GB (Q2_K) to 431.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 149.3 GB (11 parts) | 154.1 GB | Too big | Get file → | |
| Q3_K_M | 195.4 GB (15 parts) | 200.1 GB | Too big | Get file → | |
| Q8_0 | 431.2 GB (32 parts) | 436.0 GB | Too big | Get file → |
What GPU do you need for nicoboss.Hermes 3 Llama 3.1 405B Uncensored?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which nicoboss.Hermes 3 Llama 3.1 405B Uncensored quant should you choose?
Q3_K_M (195.4 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 149.3 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 nicoboss.Hermes 3 Llama 3.1 405B Uncensored
How much VRAM does nicoboss.Hermes 3 Llama 3.1 405B Uncensored need?
About 200.1 GB at Q3_K_M with an 8K context window. That is the 195.4 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 nicoboss.Hermes 3 Llama 3.1 405B Uncensored on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 154.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of nicoboss.Hermes 3 Llama 3.1 405B Uncensored GGUF?
It depends on the quant: Q2_K is 149.3 GB, Q3_K_M is 195.4 GB, Q8_0 is 431.2 GB.
What context length does nicoboss.Hermes 3 Llama 3.1 405B Uncensored support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.9 GB at 32K.
Where can I download nicoboss.Hermes 3 Llama 3.1 405B Uncensored GGUF?
The files are on Hugging Face in the llmtraining-scraper/uncensored repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does nicoboss.Hermes 3 Llama 3.1 405B Uncensored use?
Hugging Face lists the license as llama3.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.