NousResearch.Hermes 4 405B needs about 247.8 GB of memory at Q4_K_M (a 243.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 12 quants, from 0.1 GB to 811.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.9 GB.
Hermes 4 405B – a large Llama‑3.1 based reasoning model
Hermes 4 405B is a 405‑billion‑parameter Llama‑3.1 model with a 131072‑token context window. It is trained on a large post‑training corpus focused on reasoning, math, code, STEM, logic, and structured outputs. The model supports tool use and is aligned to user values.
Good at
- High‑quality reasoning and math
- Structured JSON output
- Tool‑aware responses
Limits
- No vision support
- Large VRAM requirement for full precision
- License is llama3
Best for
- Complex problem solving
- Code generation with tool integration
- Scientific data analysis
Who it’s for. Developers and researchers needing a large, reasoning‑capable model for advanced applications. The model is suitable for use in llama.cpp environments where memory can be allocated for large quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 4.8 GB | Fits | Get file → | |
| IQ1_M | 93.5 GB (7 parts) | 98.2 GB | Too big | Get file → | |
| IQ2_XXS | 107.3 GB (8 parts) | 112.0 GB | Too big | Get file → | |
| IQ2_XS | 119.3 GB (9 parts) | 124.1 GB | Too big | Get file → | |
| IQ2_S | 125.6 GB (9 parts) | 130.4 GB | Too big | Get file → | |
| 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 → | |
| Q4_K_M | 243.1 GB (18 parts) | 247.8 GB | Too big | Get file → | |
| Q5_K_M | 286.6 GB (22 parts) | 291.4 GB | Too big | Get file → | |
| Q6_K | 332.9 GB (25 parts) | 337.7 GB | Too big | Get file → | |
| Q8_0 | 431.2 GB (32 parts) | 436.0 GB | Too big | Get file → | |
| F16 | 811.7 GB (55 parts) | 816.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (247.8 GB memory estimate). For 16 GB VRAM, Q5_K_M (291.4 GB estimate) or Q6_K (337.7 GB). For 32 GB VRAM, Q8_0 (436 GB estimate) or F16 (816.5 GB). Estimates are approximate.
What GPU do you need for NousResearch.Hermes 4 405B?
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 the main file (0.1 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 4.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 4.8 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 4.8 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 4.8 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 4.8 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 4.8 GB in use).
Which NousResearch.Hermes 4 405B quant should you choose?
Q4_K_M is the usual starting point for NousResearch.Hermes 4 405B: it balances file size and quality well. Here it is a 243.1 GB file.
The Q8_0 file is 431.2 GB, about 1.8 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 the first one in the table at 0.1 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
Source
Frequently asked questions about NousResearch.Hermes 4 405B
How much VRAM does NousResearch.Hermes 4 405B need?
About 247.8 GB at Q4_K_M with an 8K context window. That is the 243.1 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 NousResearch.Hermes 4 405B on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NousResearch.Hermes 4 405B GGUF?
It depends on the quant: file is 0.1 GB, IQ1_M is 93.5 GB, IQ2_XXS is 107.3 GB, IQ2_XS is 119.3 GB, IQ2_S is 125.6 GB, Q2_K is 149.3 GB and 6 more.
What context length does NousResearch.Hermes 4 405B 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 NousResearch.Hermes 4 405B GGUF?
The files are on Hugging Face in the DevQuasar-13/NousResearch.Hermes-4-405B-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 NousResearch.Hermes 4 405B use?
Hugging Face lists the license as llama3. 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 Hermes 4 405B on 8 GB VRAM?
Use the Q4_K_M quantization; it requires about 247.8 GB of VRAM at 8 k context, which is not feasible on 8 GB. Smaller quantizations are not available.
Does Hermes 4 support vision?
No, the model has no vision capabilities.
What license does Hermes 4 use?
The model is licensed under llama3.