MN DARKEST UNIVERSE 29B by DavidAU

 »  All LLMs  »  DavidAU  »  MN DARKEST UNIVERSE 29B   URL Share it on

MN DARKEST UNIVERSE 29B is an open-source language model by DavidAU. Features: 12b LLM, VRAM: 44GB, Context: 1000K, Instruction-Based, LLM Explorer Score: 0.16.

  128k context   All genres   Autotrain compatible Base model:anthracite-org/magn... Base model:davidau/mn-18.5b-ce... Base model:davidau/mn-magnum-v... Base model:davidau/mn-rocinant... Base model:merge:anthracite-or... Base model:merge:davidau/mn-18... Base model:merge:davidau/mn-ma... Base model:merge:davidau/mn-ro... Base model:merge:mistralai/mis... Base model:merge:nothingiisrea... Base model:merge:thedrummer/ro... Base model:mistralai/mistral-n... Base model:nothingiisreal/mn-1... Base model:thedrummer/rocinant...   Bfloat16   Brainstorm 40x   Creative   Creative writing   Endpoints compatible   Fiction   Fiction story   Fiction writing   Horror   Instruct   Merge   Mergekit   Mistral   Mistral nemo   Mistral nemo instruct   Mn   Plot generation   Region:us   Roleplaying   Romance   Rp   Safetensors   Scene continue   Science fiction   Sharded   Story   Story generation   Storytelling   Sub-plot generation   Swearing   Tensorflow   Vivid prosing   Vivid writing   Writing

MN DARKEST UNIVERSE 29B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

MN DARKEST UNIVERSE 29B Parameters and Internals

LLM NameMN DARKEST UNIVERSE 29B
Repository 🤗https://huggingface.co/DavidAU/MN-DARKEST-UNIVERSE-29B 
Base Model(s)  Mistral Nemo Instruct 2407   TheDrummer/Rocinante-12B-v1.1   anthracite-org/magnum-v2.5-12b-kto   nothingiisreal/MN-12B-Celeste-V1.9   DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct   DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct   DavidAU/MN-Rocinante-18.5B-v1.1-Instruct   mistralai/Mistral-Nemo-Instruct-2407   TheDrummer/Rocinante-12B-v1.1   anthracite-org/magnum-v2.5-12b-kto   nothingiisreal/MN-12B-Celeste-V1.9   DavidAU/MN-18.5B-Celeste-V1.9-Story-Wizard-ED1-Instruct   DavidAU/MN-magnum-v2.5-18.5B-kto-Instruct   DavidAU/MN-Rocinante-18.5B-v1.1-Instruct
Model Size12b
Required VRAM44 GB
Updated2025-11-05
MaintainerDavidAU
Model Typemistral
Instruction-BasedYes
Model Files  1.3 GB: 1-of-62   1.3 GB: 2-of-62   1.0 GB: 3-of-62   0.9 GB: 4-of-62   0.9 GB: 5-of-62   0.9 GB: 6-of-62   1.0 GB: 7-of-62   0.9 GB: 8-of-62   0.9 GB: 9-of-62   0.9 GB: 10-of-62   1.0 GB: 11-of-62   0.9 GB: 12-of-62   0.9 GB: 13-of-62   0.9 GB: 14-of-62   1.0 GB: 15-of-62   0.9 GB: 16-of-62   0.9 GB: 17-of-62   0.9 GB: 18-of-62   1.0 GB: 19-of-62   0.9 GB: 20-of-62   0.9 GB: 21-of-62   0.9 GB: 22-of-62   1.0 GB: 23-of-62   0.9 GB: 24-of-62   0.9 GB: 25-of-62   0.9 GB: 26-of-62   1.0 GB: 27-of-62   0.9 GB: 28-of-62   0.9 GB: 29-of-62   0.9 GB: 30-of-62   1.0 GB: 31-of-62   0.9 GB: 32-of-62   0.9 GB: 33-of-62   0.9 GB: 34-of-62   1.0 GB: 35-of-62   0.9 GB: 36-of-62   0.9 GB: 37-of-62   0.9 GB: 38-of-62   0.9 GB: 39-of-62   0.9 GB: 40-of-62   0.9 GB: 41-of-62   0.9 GB: 42-of-62   0.9 GB: 43-of-62   0.9 GB: 44-of-62   0.9 GB: 45-of-62   0.9 GB: 46-of-62   0.9 GB: 47-of-62
Model ArchitectureMistralForCausalLM
Context Length1024000
Model Max Length1024000
Transformers Version4.46.0
Vocabulary Size131074
Torch Data Typebfloat16

Best Alternatives to MN DARKEST UNIVERSE 29B

Best Alternatives
Context / RAM
Downloads
Likes
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB1510138
Impish Nemo 12B1000K / 24.5 GB207870
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB127622
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 GB778
Note: green Score (e.g. "73.2") means that the model is better than DavidAU/MN-DARKEST-UNIVERSE-29B.

Rank the MN DARKEST UNIVERSE 29B 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? 53640 in total.

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