MI

Nous Hermes 2 Mixtral 8x7B SFT

MistralGGUF by second-stateUpdated 2024-03-20
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant17.3 GB
Quick answer

Nous Hermes 2 Mixtral 8x7B SFT needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 12 quants, from 17.3 GB (Q2_K) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Nous Hermes 2 Mixtral 8x7B SFT – 46.7B parameter Mixture of Experts model

Nous Hermes 2 Mixtral 8x7B SFT is a supervised fine‑tuned version of the Mixtral 8x7B MoE LLM. It contains 46.7B parameters and supports a 32,768 token context window. The model is released under the apache‑2.0 license.

Good at

  • Tool use and instruction following
  • ChatML prompt format
  • Large context handling

Limits

  • Requires 8,000 token context for memory estimates
  • No vision capabilities
  • Mixture of Experts architecture limits single‑GPU inference

Best for

  • Chatbot applications needing tool integration
  • Complex instruction following tasks
  • Long‑form dialogue generation

Who it’s for. Developers building chat interfaces that need robust tool use and long context support. Researchers testing Mixture of Experts models in a supervised fine‑tune setting.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.3 GB 18.9 GB
Too big Get file →
Q3_K_S20.4 GB 22.0 GB
Too big Get file →
Q3_K_M22.5 GB 24.1 GB
Too big Get file →
Q3_K_L24.2 GB 25.7 GB
Too big Get file →
Q4_026.4 GB 28.0 GB
Too big Get file →
Q4_K_S26.7 GB 28.3 GB
Too big Get file →
Q4_K_M28.4 GB 30.0 GB
Too big Get file →
Q5_032.2 GB 33.8 GB
Too big Get file →
Q5_K_S32.2 GB 33.8 GB
Too big Get file →
Q5_K_M33.2 GB 34.8 GB
Too big Get file →
Q6_K38.4 GB 40.0 GB
Too big Get file →
Q8_049.6 GB 51.2 GB
Too big Get file →

For 8‑GB VRAM use Q4_0 or Q4_K_S (file size 26.44 GB, estimated 28 GB memory). For 12‑GB VRAM use Q5_0 or Q5_K_S (32.23 GB, 33.8 GB memory). For 24‑GB VRAM use Q6_K (38.38 GB, 40 GB memory).

What GPU do you need for Nous Hermes 2 Mixtral 8x7B SFT?

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_S (20.4 GB file, about 22.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).

Which Nous Hermes 2 Mixtral 8x7B SFT quant should you choose?

Q4_K_M is the usual starting point for Nous Hermes 2 Mixtral 8x7B SFT: it balances file size and quality well. Here it is a 28.4 GB file.

The Q8_0 file is 49.6 GB, about 1.7 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 Q2_K at 17.3 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

Architecturellama
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bysecond-state
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,589
Last updated2024-03-20

Frequently asked questions about Nous Hermes 2 Mixtral 8x7B SFT

How much VRAM does Nous Hermes 2 Mixtral 8x7B SFT need?

About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 Mixtral 8x7B SFT on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nous Hermes 2 Mixtral 8x7B SFT GGUF?

It depends on the quant: Q2_K is 17.3 GB, Q3_K_S is 20.4 GB, Q3_K_M is 22.5 GB, Q3_K_L is 24.2 GB, Q4_0 is 26.4 GB, Q4_K_S is 26.7 GB and 6 more.

What context length does Nous Hermes 2 Mixtral 8x7B SFT support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Nous Hermes 2 Mixtral 8x7B SFT GGUF?

The files are on Hugging Face in the second-state/Nous-Hermes-2-Mixtral-8x7B-SFT-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 Mixtral 8x7B SFT 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.

Can I run this model on 8 GB VRAM?

Use the Q4_0 or Q4_K_S quantized file; it requires about 28 GB of memory at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

What prompt format does it use?

It uses the ChatML prompt format compatible with OpenAI chat APIs.

Other GGUFs of Nous-Hermes-2-Mixtral-8x7B-SFT

Similar models

Browse all →

More from second-state

All by second-state →

More Mistral models

All Mistral →

Other large models

All large models →