Nous Hermes 2 MoE 2x34B needs about 39.2 GB of memory at Q4_K_M (a 36.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 22.4 GB (Q2_K) to 49.9 GB (Q6_K).
Nous Hermes 2 MoE 2x34B is a 60.8B-parameter Nous model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 10 quant files, from 22.4 GB (Q2_K) to 49.9 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 22.4 GB | 23.9 GB | Too big | Get file → | |
| Q3_K_S | 26.3 GB | 27.8 GB | Too big | Get file → | |
| Q3_K_M | 29.2 GB | 30.7 GB | Too big | Get file → | |
| Q3_K_L | 31.8 GB | 33.3 GB | Too big | Get file → | |
| IQ4_XS | 32.8 GB | 34.3 GB | Too big | Get file → | |
| Q4_K_S | 34.6 GB | 36.1 GB | Too big | Get file → | |
| Q4_K_M | 36.7 GB | 38.2 GB | Too big | Get file → | |
| Q5_K_S | 41.9 GB | 43.4 GB | Too big | Get file → | |
| Q5_K_M | 43.1 GB | 44.6 GB | Too big | Get file → | |
| Q6_K | 49.9 GB | 51.4 GB | Too big | Get file → |
What GPU do you need for Nous Hermes 2 MoE 2x34B?
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: the best quant that fits is Q3_K_M (29.2 GB file, about 31.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (43.1 GB file, about 45.6 GB in use).
Which Nous Hermes 2 MoE 2x34B quant should you choose?
Q4_K_M is the usual starting point for Nous Hermes 2 MoE 2x34B: it balances file size and quality well. Here it is a 36.7 GB file.
If memory is tight, the smallest file is Q2_K at 22.4 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 Nous Hermes 2 MoE 2x34B
How much VRAM does Nous Hermes 2 MoE 2x34B need?
About 39.2 GB at Q4_K_M with an 8K context window. That is the 36.7 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 MoE 2x34B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nous Hermes 2 MoE 2x34B GGUF?
It depends on the quant: Q2_K is 22.4 GB, Q3_K_S is 26.3 GB, Q3_K_M is 29.2 GB, Q3_K_L is 31.8 GB, IQ4_XS is 32.8 GB, Q4_K_S is 34.6 GB and 4 more.
What context length does Nous Hermes 2 MoE 2x34B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.0 GB at 8K and 1.0 GB at 4K.
Where can I download Nous Hermes 2 MoE 2x34B GGUF?
The files are on Hugging Face in the mradermacher/Nous-Hermes-2-MoE-2x34B-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 MoE 2x34B 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.