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 9 quants, from 87.2 GB (IQ1_S) to 811.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.9 GB.
Hermes‑4‑405B: 405B‑parameter Llama‑3.1 hybrid‑mode reasoning model
Hermes‑4‑405B is a 405‑billion‑parameter Llama‑3.1 model with hybrid reasoning. It supports roleplay, tools, and advanced reasoning. The model is trained on a large post‑training corpus and follows the Llama‑3‑Chat format.
Good at
- Advanced reasoning
- Structured JSON output
- Creative writing
Limits
- No vision support
- Large VRAM requirement
- License: llama3
Best for
- Complex problem solving
- Code generation
- Data analysis
Who it’s for. Developers and researchers needing high‑quality reasoning and structured outputs. The model is suitable for applications that require detailed explanations and JSON‑compliant results.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 87.2 GB (2 parts) | 91.9 GB | Too big | Get file → | |
| IQ1_M | 94.7 GB (2 parts) | 99.5 GB | Too big | Get file → | |
| Q2_K_XL | 151.4 GB (4 parts) | 156.1 GB | Too big | Get file → | |
| Q3_K_XL | 197.4 GB (4 parts) | 202.1 GB | Too big | Get file → | |
| Q4_K_M | 243.1 GB (5 parts) | 247.8 GB | Too big | Get file → | |
| Q4_K_XL | 243.7 GB (5 parts) | 248.4 GB | Too big | Get file → | |
| Q5_K_XL | 286.5 GB (6 parts) | 291.2 GB | Too big | Get file → | |
| Q8_0 | 431.2 GB (9 parts) | 436.0 GB | Too big | Get file → | |
| BF16 | 811.7 GB (17 parts) | 816.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S or IQ1_M (file sizes 87.22 GB and 94.73 GB). For 16 GB VRAM, Q4_K_M or Q4_K_XL (file sizes 243.07 GB and 243.72 GB). For 32 GB VRAM, Q5_K_XL (286.5 GB). Estimates are approximate.
What GPU do you need for 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: 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 Hermes-4-405B quant should you choose?
Q4_K_M is the usual starting point for 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 IQ1_S at 87.2 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 Hermes-4-405B
How much VRAM does 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 Hermes-4-405B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 91.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Hermes-4-405B GGUF?
It depends on the quant: IQ1_S is 87.2 GB, IQ1_M is 94.7 GB, Q2_K_XL is 151.4 GB, Q3_K_XL is 197.4 GB, Q4_K_M is 243.1 GB, Q4_K_XL is 243.7 GB and 3 more.
What context length does 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 Hermes-4-405B GGUF?
The files are on Hugging Face in the unsloth/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 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 IQ1_S or IQ1_M quantization; they require about 92 GB and 100 GB of VRAM at 8 k context.
Does Hermes‑4‑405B support vision?
No, the model has no vision capability.