MI

nousresearch_nous-hermes-2-mixtral-8x7b-sft

MistralGGUF by TheBlokeUpdated 2024-01-16
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant17.3 GB
Quick answer

nousresearch_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 8 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 LLM with tool use

Nous Hermes 2 Mixtral 8x7B SFT is a 46.7B parameter model trained on over 1,000,000 GPT‑4 generated entries. It supports tool use and is available in GGUF format. The model is licensed under apache‑2.0.

Good at

  • Tool‑enabled dialogue
  • Large context handling
  • High‑quality code generation

Limits

  • Requires 32768 token context
  • No vision support
  • Large VRAM needed for full precision

Best for

  • Chatbot with tool integration
  • Code assistance
  • Complex reasoning tasks

Who it’s for. Developers and researchers needing a large, tool‑aware LLM for local deployment. The model is suitable for applications that can accommodate its memory footprint and context length.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K17.3 GB 18.9 GB
Too big Get file →
Q3_K_M22.5 GB 24.1 GB
Too big Get file →
Q4_026.4 GB 28.0 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_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 Q2_K (17.31 GB file, 18.9 GB memory). For 16 GB VRAM, Q4_0 (26.44 GB file, 28 GB memory). For 24 GB VRAM, Q5_K_M (33.23 GB file, 34.8 GB memory).

What GPU do you need for nousresearch_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 Q2_K (17.3 GB file, about 18.9 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 nousresearch_nous-hermes-2-mixtral-8x7b-sft quant should you choose?

Q4_K_M is the usual starting point for nousresearch_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 byTheBloke
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,688
Last updated2024-01-16

Frequently asked questions about nousresearch_nous-hermes-2-mixtral-8x7b-sft

How much VRAM does nousresearch_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 nousresearch_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 nousresearch_nous-hermes-2-mixtral-8x7b-sft GGUF?

It depends on the quant: Q2_K is 17.3 GB, Q3_K_M is 22.5 GB, Q4_0 is 26.4 GB, Q4_K_M is 28.4 GB, Q5_0 is 32.2 GB, Q5_K_M is 33.2 GB and 2 more.

What context length does nousresearch_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 nousresearch_nous-hermes-2-mixtral-8x7b-sft GGUF?

The files are on Hugging Face in the TheBloke/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 nousresearch_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?

Yes, using the Q2_K quantized file which requires 18.9 GB of VRAM at 8 k context.

Does the model support vision?

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 TheBloke

All by TheBloke →

More Mistral models

All Mistral →

Other large models

All large models →