Hermes 4_3_36b needs about 24.4 GB of memory at Q4_K_M (a 21.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 17.6 GB (Q3_K_M) to 72.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Hermes 4_3_36b is a 36.2B-parameter Seed model in GGUF format, quantized by genevaquant. Its trained context length is 512K tokens. The repository has 6 quant files, from 17.6 GB (Q3_K_M) to 72.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 17.6 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_M | 21.8 GB | 24.4 GB | Too big | Get file → | |
| Q5_K_M | 25.6 GB | 28.2 GB | Too big | Get file → | |
| Q6_K | 29.7 GB | 32.3 GB | Too big | Get file → | |
| Q8_0 | 38.4 GB | 41.1 GB | Too big | Get file → | |
| — | 72.3 GB | 75.0 GB | Too big | Get file → |
What GPU do you need for Hermes 4_3_36b?
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 Q3_K_M (17.6 GB file, about 20.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (25.6 GB file, about 28.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (38.4 GB file, about 41.1 GB in use).
Which Hermes 4_3_36b quant should you choose?
Q4_K_M is the usual starting point for Hermes 4_3_36b: it balances file size and quality well. Here it is a 21.8 GB file.
The Q8_0 file is 38.4 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 Q3_K_M at 17.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hermes 4_3_36b
How much VRAM does Hermes 4_3_36b need?
About 24.4 GB at Q4_K_M with an 8K context window. That is the 21.8 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_3_36b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Hermes 4_3_36b GGUF?
It depends on the quant: Q3_K_M is 17.6 GB, Q4_K_M is 21.8 GB, Q5_K_M is 25.6 GB, Q6_K is 29.7 GB, Q8_0 is 38.4 GB, file is 72.3 GB.
What context length does Hermes 4_3_36b support?
The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Hermes 4_3_36b GGUF?
The files are on Hugging Face in the genevaquant/Hermes-4.3-36B-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_3_36b 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.