NousResearch.Hermes 4 70B needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 0.0 GB to 75.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
NousResearch.Hermes 4 70B is a 70.6B-parameter Hermes model in GGUF format, quantized by DevQuasar. Its trained context length is 128K tokens. The repository has 11 quant files, from 0.0 GB to 75.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.2 GB | Fits | Get file → | |
| IQ1_M | 16.8 GB | 19.9 GB | Too big | Get file → | |
| IQ2_XXS | 19.1 GB | 22.3 GB | Too big | Get file → | |
| IQ2_XS | 21.1 GB | 24.3 GB | Too big | Get file → | |
| IQ2_S | 22.2 GB | 25.4 GB | Too big | Get file → | |
| Q2_K | 26.4 GB | 29.6 GB | Too big | Get file → | |
| Q3_K_M | 34.3 GB | 37.5 GB | Too big | Get file → | |
| Q4_K_M | 42.5 GB (4 parts) | 45.7 GB | Too big | Get file → | |
| Q5_K_M | 49.9 GB (4 parts) | 53.1 GB | Too big | Get file → | |
| Q6_K | 57.9 GB (5 parts) | 61.1 GB | Too big | Get file → | |
| Q8_0 | 75.0 GB (6 parts) | 78.2 GB | Too big | Get file → |
What GPU do you need for NousResearch.Hermes 4 70B?
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: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 24 GB VRAM: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).
Which NousResearch.Hermes 4 70B quant should you choose?
Q4_K_M is the usual starting point for NousResearch.Hermes 4 70B: it balances file size and quality well. Here it is a 42.5 GB file.
The Q8_0 file is 75.0 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 0.0 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 70B
How much VRAM does NousResearch.Hermes 4 70B need?
About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 NousResearch.Hermes 4 70B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NousResearch.Hermes 4 70B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, Q2_K is 26.4 GB and 5 more.
What context length does NousResearch.Hermes 4 70B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download NousResearch.Hermes 4 70B GGUF?
The files are on Hugging Face in the DevQuasar/NousResearch.Hermes-4-70B-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 70B 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.