MI

DeepHermes 3 Mistral 24B Preview

MistralGGUF by NousResearchUpdated 2025-03-13
Download on Hugging Face
Parameters23.6B
Context32K
Layers40
Architecturellama
Smallest quant13.4 GB
Quick answer

DeepHermes 3 Mistral 24B Preview needs about 18.1 GB of memory at its main file (a 16.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 13.4 GB to 25.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

DeepHermes 3 Mistral 24B Preview – a 24B parameter LLM with 32k context

DeepHermes 3 Mistral 24B Preview is a 23.6B parameter model based on Mistral Small 24B. It supports long‑chain reasoning, roleplay, and tool usage. The model is released under Apache‑2.0 and offers a 32k token context window.

Good at

  • Long‑chain reasoning
  • Roleplay
  • Tool calling

Limits

  • No vision support
  • Large memory requirement
  • No mixed‑expert architecture

Best for

  • Complex reasoning tasks
  • Interactive role‑play scenarios
  • Tool‑integrated workflows

Who it’s for. Developers and researchers needing a large, reasoning‑capable LLM that can be run locally. The model is open‑source and can be fine‑tuned or integrated into custom applications.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—13.4 GB 15.3 GB
Too big Get file →
—16.3 GB 18.1 GB
Too big Get file →
—19.3 GB 21.2 GB
Too big Get file →
—25.1 GB 26.9 GB
Too big Get file →

For 8‑GB VRAM use the 13.44‑GB file; it requires about 15.3‑GB memory at 8k context. For 12‑GB VRAM use the 16.3‑GB file (18.1‑GB memory). For 16‑GB VRAM use the 19.35‑GB file (21.2‑GB memory). For 24‑GB VRAM use the 25.05‑GB file (26.9‑GB memory).

What GPU do you need for DeepHermes 3 Mistral 24B Preview?

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: the best quant that fits is the main file (13.4 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (19.3 GB file, about 21.2 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (25.1 GB file, about 26.9 GB in use).

Which DeepHermes 3 Mistral 24B Preview quant should you choose?

If memory is tight, the smallest file is the first one in the table at 13.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byNousResearch
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,174
Last updated2025-03-13

Frequently asked questions about DeepHermes 3 Mistral 24B Preview

How much VRAM does DeepHermes 3 Mistral 24B Preview need?

About 18.1 GB at its main file with an 8K context window. That is the 16.3 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 DeepHermes 3 Mistral 24B Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepHermes 3 Mistral 24B Preview GGUF?

It depends on the quant: file is 13.4 GB, file is 16.3 GB, file is 19.3 GB, file is 25.1 GB.

What context length does DeepHermes 3 Mistral 24B Preview support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download DeepHermes 3 Mistral 24B Preview GGUF?

The files are on Hugging Face in the NousResearch/DeepHermes-3-Mistral-24B-Preview-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 DeepHermes 3 Mistral 24B Preview 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 DeepHermes 3 on 8 GB VRAM?

The 13.44‑GB quant requires about 15.3‑GB memory at 8k context, so 8‑GB VRAM is insufficient.

Does DeepHermes 3 support vision tasks?

No, the model has no vision capability.

What license does DeepHermes 3 use?

Apache‑2.0, allowing commercial and non‑commercial use.

Other GGUFs of Mistral-Small-24B-Base-2501

Similar models

Browse all →

More from NousResearch

All by NousResearch →

More Mistral models

All Mistral →

Other medium models

All medium models →