Asinello Minerva 3B V0.1 by mudler

 »  All LLMs  »  mudler  »  Asinello Minerva 3B V0.1   URL Share it on

Asinello Minerva 3B V0.1 is an open-source language model by mudler. Features: 3b LLM, VRAM: 5.8GB, Context: 16K, License: apache-2.0, LLM Explorer Score: 0.14.

  Conversational   Deploy:azure   Endpoints compatible   Llama-factory   Mistral   Region:us   Safetensors   Sharded   Tensorflow

Asinello Minerva 3B V0.1 Benchmarks

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

Asinello Minerva 3B V0.1 Parameters and Internals

Model Type 
Mistral
Additional Notes 
This model is a fine-tune of the Minerva model on a custom dataset.
Supported Languages 
Italian (NLP)
Training Details 
Data Sources:
Asinello
LLM NameAsinello Minerva 3B V0.1
Repository 🤗https://huggingface.co/mudler/Asinello-Minerva-3B-v0.1 
Model Size3b
Required VRAM5.8 GB
Updated2026-05-19
Maintainermudler
Model Typemistral
Model Files  2.0 GB: 1-of-3   2.0 GB: 2-of-3   1.8 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Asinello Minerva 3B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Ministral 3B Instruct128K / 6.7 GB773784
Mistral 3.3B128K / 6.6 GB2011
Mistral 3B Instruct V0.232K / 11.5 GB314
Mallam 3B 409632K / 6.1 GB282
Dummy Mistral 3B32K / 18.2 GB171
Minerva 3B Ties 1.016K / 5.8 GB10500
...inerva 3B Llama3 Instruct V0.116K / 5.8 GB12520
Minerva 3B Instruct V1.016K / 5.8 GB677
Minerva 3B Base RAG16K / 5.8 GB1413
Minerva 3B Instruct V1.016K / 5.8 GB127
Note: green Score (e.g. "73.2") means that the model is better than mudler/Asinello-Minerva-3B-v0.1.

Rank the Asinello Minerva 3B V0.1 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.

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