Nous Hermes 2 Llama 2 70B iMat needs about 23.5 GB of memory at IQ2_XS (a 20.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 14.5 GB (IQ1_S) to 33.3 GB (Q3_K_M).
Nous Hermes 2 Llama 2 70B iMat is a 69B-parameter Llama model in GGUF format, quantized by NexesQuants. Its trained context length is 4K tokens. The repository has 3 quant files, from 14.5 GB (IQ1_S) to 33.3 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 14.5 GB | 16.4 GB | Too big | Get file → | |
| IQ2_XS | 20.3 GB | 22.2 GB | Too big | Get file → | |
| Q3_K_M | 33.3 GB | 35.1 GB | Too big | Get file → |
What GPU do you need for Nous Hermes 2 Llama 2 70B iMat?
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 IQ2_XS (20.3 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is IQ2_XS (20.3 GB file, about 23.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q3_K_M (33.3 GB file, about 36.5 GB in use).
Which Nous Hermes 2 Llama 2 70B iMat quant should you choose?
IQ2_XS (20.3 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 14.5 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
Frequently asked questions about Nous Hermes 2 Llama 2 70B iMat
How much VRAM does Nous Hermes 2 Llama 2 70B iMat need?
About 23.5 GB at IQ2_XS with an 8K context window. That is the 20.3 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 Nous Hermes 2 Llama 2 70B iMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nous Hermes 2 Llama 2 70B iMat GGUF?
It depends on the quant: IQ1_S is 14.5 GB, IQ2_XS is 20.3 GB, Q3_K_M is 33.3 GB.
What context length does Nous Hermes 2 Llama 2 70B iMat support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download Nous Hermes 2 Llama 2 70B iMat GGUF?
The files are on Hugging Face in the NexesQuants/Nous-Hermes-2-Llama-2-70B-iMat.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 Nous Hermes 2 Llama 2 70B iMat use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.