MI

Nous-Hermes-2-Mixtral-8x7B-SFT

MistralGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant9.8 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 21 quants, from 9.8 GB (IQ1_S) to 38.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Nous-Hermes-2-Mixtral-8x7B-SFT, a 46.7B parameter Mixture of Experts model fine‑tuned on GPT‑4 data

The model is a supervised finetune of the Mixtral 8x7B MoE architecture. It contains 46.7B parameters and was trained on over 1,000,000 GPT‑4 generated entries. The model supports the ChatML prompt format and includes a tools ability.

Good at

  • Chat‑style dialogue
  • Tool‑based instruction following
  • Large context handling

Limits

  • Requires 32,768 token context
  • No vision support
  • Apache‑2.0 license

Best for

  • Chatbot development
  • Code generation with tool calls
  • Long‑form content creation

Who it’s for. Developers building chat‑based applications that need a large, tool‑aware LLM. The model is suitable for those who can provide sufficient GPU memory for inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S9.8 GB 11.4 GB
Too big Get file →
IQ1_M10.8 GB 12.4 GB
Too big Get file →
IQ2_XXS12.6 GB 14.1 GB
Too big Get file →
IQ2_XS13.9 GB 15.5 GB
Too big Get file →
IQ2_S14.1 GB 15.7 GB
Too big Get file →
IQ2_M15.5 GB 17.1 GB
Too big Get file →
Q2_K17.3 GB 18.9 GB
Too big Get file →
IQ3_XXS18.2 GB 19.8 GB
Too big Get file →
IQ3_XS19.4 GB 20.9 GB
Too big Get file →
IQ3_S20.4 GB 22.0 GB
Too big Get file →
Q3_K_S20.4 GB 22.0 GB
Too big Get file →
IQ3_M21.4 GB 23.0 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 →
IQ4_XS25.1 GB 26.7 GB
Too big Get file →
Q4_026.6 GB 28.1 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_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 →

For 8 GB VRAM, use IQ1_S (9.82 GB file, 11.4 GB memory). For 16 GB VRAM, IQ2_S (14.13 GB file, 15.7 GB memory) or Q3_K_S (20.43 GB file, 22 GB memory). For 24 GB VRAM, Q4_K_M (28.45 GB file, 30 GB memory) offers a balance of size and performance.

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: the best quant that fits is IQ1_S (9.8 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_S (14.1 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_M (21.4 GB file, about 23.0 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.

If memory is tight, the smallest file is IQ1_S at 9.8 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 bymradermacher
FamilyMistral
Licenseapache-2.0
Downloads (HF)3,129
Last updated2024-08-02

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 11.4 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: IQ1_S is 9.8 GB, IQ1_M is 10.8 GB, IQ2_XXS is 12.6 GB, IQ2_XS is 13.9 GB, IQ2_S is 14.1 GB, IQ2_M is 15.5 GB and 15 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 mradermacher/Nous-Hermes-2-Mixtral-8x7B-SFT-i1-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 IQ1_S quant, which requires 11.4 GB of VRAM at 8 k context. It will fit on 8 GB with swapping or lower context.

Does the model support image inputs?

No, the model has no vision capability.

What license applies to this model?

The model is released under the Apache‑2.0 license.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other large models

All large models →