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

MN Magnum V2.5 18.5B Kto Instruct by DavidAU

 »  All LLMs  »  DavidAU  »  MN Magnum V2.5 18.5B Kto Instruct   URL Share it on

  5   

MN Magnum V2.5 18.5B Kto Instruct is an open-source language model by DavidAU. Features: 12b LLM, VRAM: 36.2GB, Context: 1000K, Instruction-Based, Merged, LLM Explorer Score: 0.15.

  Merged Model   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct 

MN Magnum V2.5 18.5B Kto Instruct Benchmarks

LLME Score: 0.1468
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MN Magnum V2.5 18.5B Kto Instruct (DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct)
🌟 Advertise your project 🚀

MN Magnum V2.5 18.5B Kto Instruct Parameters and Internals

Additional Notes 
This model is a merge of pre-trained language models created using mergekit with the passthrough merge method.
LLM NameMN Magnum V2.5 18.5B Kto Instruct
Repository 🤗https://huggingface.co/DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct 
Merged ModelYes
Model Size12b
Required VRAM36.2 GB
Updated2025-09-23
MaintainerDavidAU
Model Typemistral
Instruction-BasedYes
Model Files  1.3 GB: 1-of-38   1.3 GB: 2-of-38   1.0 GB: 3-of-38   1.0 GB: 4-of-38   0.9 GB: 5-of-38   0.9 GB: 6-of-38   0.9 GB: 7-of-38   0.9 GB: 8-of-38   0.9 GB: 9-of-38   0.9 GB: 10-of-38   1.0 GB: 11-of-38   1.0 GB: 12-of-38   0.9 GB: 13-of-38   0.9 GB: 14-of-38   1.0 GB: 15-of-38   1.0 GB: 16-of-38   0.9 GB: 17-of-38   0.9 GB: 18-of-38   0.9 GB: 19-of-38   0.9 GB: 20-of-38   0.9 GB: 21-of-38   0.9 GB: 22-of-38   1.0 GB: 23-of-38   1.0 GB: 24-of-38   0.9 GB: 25-of-38   0.9 GB: 26-of-38   1.0 GB: 27-of-38   1.0 GB: 28-of-38   1.0 GB: 29-of-38   0.9 GB: 30-of-38   0.9 GB: 31-of-38   1.0 GB: 32-of-38   0.9 GB: 33-of-38   0.9 GB: 34-of-38   0.9 GB: 35-of-38   1.0 GB: 36-of-38   0.9 GB: 37-of-38   0.8 GB: 38-of-38
Model ArchitectureMistralForCausalLM
Context Length1024000
Model Max Length1024000
Transformers Version4.43.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to MN Magnum V2.5 18.5B Kto Instruct

Best Alternatives
Context / RAM
Downloads
Likes
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB981222
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB1789139
Impish Nemo 12B1000K / 24.5 GB156384
MN Slush1000K / 24.5 GB18132
ChatWaifu V1.41000K / 24.5 GB33520
Magnum V4 12B1000K / 24.5 GB43250
ChatWaifu 12B V2.01000K / 24.5 GB17522
Kinggaroo 12B V21000K / 23.8 GB184
Mistral Nemo Bophades 12B1000K / 24.5 GB359
Mistral Nemo Wissenschaft 12B1000K / 24.5 GB228
Note: green Score (e.g. "73.2") means that the model is better than DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct.

Rank the MN Magnum V2.5 18.5B Kto Instruct 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