Ollama Library · llama
Can I run nous-hermes2-mixtral?
The Nous Hermes 2 model from Nous Research, now trained over Mixtral.
46.7B parameters32K contexttextApache License6 builds
nous-hermes2-mixtral system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| nous-hermes2-mixtral:8x7b-dpo-q4_0 | Q4_0 | 24.6 GB | ~35.6 GB(est.) |
| nous-hermes2-mixtral:8x7b-dpo-q4_K_M | Q4_K_M | 26.5 GB | ~38.3 GB(est.) |
| nous-hermes2-mixtral:8x7b-dpo-q5_K_M | Q5_K_M | 30.9 GB | ~44.6 GB(est.) |
| nous-hermes2-mixtral:8x7b-dpo-q6_K | Q6_K | 35.7 GB | ~51.5 GB(est.) |
| nous-hermes2-mixtral:8x7b-dpo-q8_0 | Q8_0 | 46.2 GB | ~66.5 GB(est.) |
| nous-hermes2-mixtral:8x7b-dpo-fp16 | F16 | 87.0 GB | ~124.8 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run nous-hermes2-mixtral locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run nous-hermes2-mixtral:8x7b-dpo-q4_0 - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about nous-hermes2-mixtral
- How much VRAM do I need to run nous-hermes2-mixtral?
- At 4K context, the smallest published build of nous-hermes2-mixtral (Q4_0) needs roughly 35.6 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run nous-hermes2-mixtral without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 35.6 GB of free RAM for the smallest build.
- How big is the nous-hermes2-mixtral download?
- The smallest published build is 24.6 GB. There are 6 builds in total, the largest being 87.0 GB. Leave some extra free disk space beyond the download itself.
- How do I run nous-hermes2-mixtral locally?
- Install Ollama, then run "ollama run nous-hermes2-mixtral:8x7b-dpo-q4_0" in a terminal. The weights download on first use and an interactive session opens.
Will nous-hermes2-mixtral run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026