LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

DeepHermes 3 Mistral 24B Preview 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  DeepHermes 3 Mistral 24B Preview 8bit   URL Share it on

  32   

DeepHermes 3 Mistral 24B Preview 8bit is an open-source language model by mlx-community. Features: 24b LLM, VRAM: 25GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.18.

  8-bit   8bit   Axolotl Base model:nousresearch/deephe... Base model:quantized:nousresea...   Chat   Chatml   Conversational   Distillation   En   Endpoints compatible   Finetuned   Function calling   Gpt4   Instruct   Json mode   Mistral   Mistral-small   Mlx   Quantized   R1   Reasoning   Region:us   Roleplaying   Safetensors   Sharded   Synthetic data   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepHermes-3-Mistral-24B-Preview-8bit 

DeepHermes 3 Mistral 24B Preview 8bit Benchmarks

LLME Score: 0.18062
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepHermes 3 Mistral 24B Preview 8bit (mlx-community/DeepHermes-3-Mistral-24B-Preview-8bit)
🌟 Advertise your project 🚀

DeepHermes 3 Mistral 24B Preview 8bit Parameters and Internals

LLM NameDeepHermes 3 Mistral 24B Preview 8bit
Repository 🤗https://huggingface.co/mlx-community/DeepHermes-3-Mistral-24B-Preview-8bit 
Base Model(s)  ...epHermes 3 Mistral 24B Preview   NousResearch/DeepHermes-3-Mistral-24B-Preview
Model Size24b
Required VRAM25 GB
Updated2026-05-06
Maintainermlx-community
Model Typemistral
Model Files  5.3 GB: 1-of-5   5.3 GB: 2-of-5   5.3 GB: 3-of-5   5.3 GB: 4-of-5   3.8 GB: 5-of-5
Supported Languagesen
Quantization Type8bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.46.3
Tokenizer ClassLlamaTokenizer
Padding Token<|end_of_text|>
Vocabulary Size131078
Torch Data Typebfloat16

Best Alternatives to DeepHermes 3 Mistral 24B Preview 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...al Small 2507 Unsloth Bnb 4bit128K / 15 GB2115
...al Small 2506 Unsloth Bnb 4bit40K / 15 GB374
Not So Small Alpaca 24B32K / 47.3 GB140
Napoleon 24B V0.032K / 47.3 GB50
...Instruct 2501 Unsloth Bnb 4bit32K / 15 GB295519
...olphin Mistral 24B Venice Fp1632K / 46.9 GB700
...all 24B Instruct 2501 Bnb 4bit32K / 14.2 GB16133
Dolphin3.0 R1 Mistral 24B 4bit32K / 13.3 GB2882
...b With Nemotron Converted Vllm32K / 47.3 GB380
...24B Base 2501 Unsloth Bnb 4bit32K / 15.7 GB2333
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/DeepHermes-3-Mistral-24B-Preview-8bit.

Rank the DeepHermes 3 Mistral 24B Preview 8bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer