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

Magnolia V3 12B by grimjim

 »  All LLMs  »  grimjim  »  Magnolia V3 12B   URL Share it on

  22   
  Merged Model   Arxiv:2212.04089   Autotrain compatible Base model:grimjim/magnum-cons... Base model:grimjim/magnum-twil... Base model:grimjim/mistralai-m... Base model:grimjim/mistralai-m... Base model:nbeerbower/mistral-... Base model:thedrummer/rocinant...   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/grimjim/Magnolia-v3-12B 

Magnolia V3 12B Benchmarks

MMLU Pro: 29.06
GPQA: 10.07
MUSR: 11.5
BBH: 32.92
IFEval: 39.65 vs 88 (so35)-54.9%
MATH Lvl 5: 13.52
LLME Score: 0.28494
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magnolia V3 12B (grimjim/Magnolia-v3-12B)

Magnolia V3 12B Parameters and Internals

LLM NameMagnolia V3 12B
Repository 🤗https://huggingface.co/grimjim/Magnolia-v3-12B 
Base Model(s)  ...stralai Mistral Nemo Base 2407   Magnum Consolidatum V1 12B   Mistral Nemo Prism 12B   TheDrummer/Rocinante-12B-v1.1   Magnum Twilight 12B   ...lai Mistral Nemo Instruct 2407   grimjim/mistralai-Mistral-Nemo-Base-2407   grimjim/magnum-consolidatum-v1-12b   nbeerbower/Mistral-Nemo-Prism-12B   TheDrummer/Rocinante-12B-v1.1   grimjim/magnum-twilight-12b   grimjim/mistralai-Mistral-Nemo-Instruct-2407
Merged ModelYes
Model Size12b
Required VRAM24.5 GB
Updated2025-05-12
Maintainergrimjim
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.46.3
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Magnolia V3 12B

Best Alternatives
Context / RAM
Downloads
Likes
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB4269119
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB326522
Francois PE V2 Huali 12B1000K / 24.5 GB848
Magnum V4 12B1000K / 24.5 GB61042
Mistral Nemo Wissenschaft 12B1000K / 24.5 GB12588
MN Slush1000K / 24.5 GB5925
ChatWaifu V1.41000K / 24.5 GB10119
Golden Curry 12B1000K / 24.5 GB1094
ChatWaifu 12B V2.01000K / 24.5 GB5220
Mistral Nemo Bophades 12B1000K / 24.5 GB829
Note: green Score (e.g. "73.2") means that the model is better than grimjim/Magnolia-v3-12B.

Rank the Magnolia V3 12B 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? 47272 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.
Release v20241227
  Support LLM Explorer