What are the hardware requirements for DeepHermes 3 Mistral 24B Preview?

DeepHermes 3 Mistral 24B Preview requires approximately 47.3 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed DeepHermes 3 Mistral 24B Preview and how large is it?

DeepHermes 3 Mistral 24B Preview is developed by NousResearch, a model with 24b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate DeepHermes 3 Mistral 24B Preview?

DeepHermes 3 Mistral 24B Preview is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

DeepHermes 3 Mistral 24B Preview by NousResearch — VRAM 47.3GB, 32K context

Name: DeepHermes 3 Mistral 24B Preview
Rating: 1 (1 reviews)
Author: NousResearch

DeepHermes 3 Mistral 24B Preview is an open-source language model by NousResearch. Features: 24b LLM, VRAM: 47.3GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.27.

Axolotl Base model:finetune:mistralai/... Base model:mistralai/mistral-s... Chat Chatml Conversational Distillation En Endpoints compatible Finetuned Function calling Gpt4 Instruct Json mode Mistral Mistral-small R1 Reasoning Region:us Roleplaying Safetensors Sharded Synthetic data Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/NousResearch/DeepHermes-3-Mistral-24B-Preview

DeepHermes 3 Mistral 24B Preview Parameters and Internals

LLM Name	DeepHermes 3 Mistral 24B Preview
Repository 🤗	https://huggingface.co/NousResearch/DeepHermes-3-Mistral-24B-Preview
Base Model(s)	Mistral Small 24B Base 2501 mistralai/Mistral-Small-24B-Base-2501
Model Size	24b
Required VRAM	47.3 GB
Updated	2026-07-26
Maintainer	NousResearch
Model Type	mistral
Model Files	4.8 GB: 1-of-10 4.8 GB: 2-of-10 4.8 GB: 3-of-10 4.9 GB: 4-of-10 4.8 GB: 5-of-10 4.8 GB: 6-of-10 4.9 GB: 7-of-10 4.8 GB: 8-of-10 4.8 GB: 9-of-10 3.9 GB: 10-of-10
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.46.3
Tokenizer Class	LlamaTokenizer
Padding Token	<\|end_of_text\|>
Vocabulary Size	131078
Torch Data Type	bfloat16

Rank the DeepHermes 3 Mistral 24B Preview capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the DeepHermes 3 Mistral 24B Preview

Model	Likes	Downloads	VRAM
...mes 3 Mistral 24B Preview 8bit	3	53	25 GB

Best Alternatives to DeepHermes 3 Mistral 24B Preview

Best Alternatives	Context / RAM	Downloads	Likes
...ral Nemo Instruct 24B Merge V1	1000K / 24.6 GB	9	0
Chaotic Order 24B V3	128K / 47.3 GB	247	1
...all 3.1 24B Instruct 2503 Text	128K / 47.3 GB	24	0
Chaotic Harmony 24B	128K / 47.3 GB	193	0
DeepWater Pleroma 24B V1	128K / 47.3 GB	151	1
Spoomplesmaxx Thrasher 24B	128K / 46.9 GB	932	3
Chaotic Order 24B V1	128K / 47.3 GB	479	0
Priest 24B V0	128K / 47.3 GB	42	1
Chaotic Order 24B V2	128K / 47.3 GB	132	4
Morbid Miasma 24B	128K / 47.3 GB	82	17

Note: green Score (e.g. "73.2") means that the model is better than NousResearch/DeepHermes-3-Mistral-24B-Preview.