What are the hardware requirements for Minerva 3B Llama3 Instruct V0.1?

Minerva 3B Llama3 Instruct V0.1 requires approximately 5.8 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Minerva 3B Llama3 Instruct V0.1 and how large is it?

Minerva 3B Llama3 Instruct V0.1 is developed by mudler, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Minerva 3B Llama3 Instruct V0.1?

Minerva 3B Llama3 Instruct V0.1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Minerva 3B Llama3 Instruct V0.1 by mudler — VRAM 5.8GB, 16K context

Name: Minerva 3B Llama3 Instruct V0.1
Author: mudler

Minerva 3B Llama3 Instruct V0.1 is an open-source language model by mudler. Features: 3b LLM, VRAM: 5.8GB, Context: 16K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.13.

Conversational Deploy:azure Endpoints compatible Instruct Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mudler/Minerva-3B-Llama3-Instruct-v0.1

Minerva 3B Llama3 Instruct V0.1 Parameters and Internals

Model Type

text generation, instruct

Additional Notes

EOS is `~~` denotes the end of the sequence.

Supported Languages

Italian (Proficient)

Training Details

Data Sources:

camoscio dataset

Methodology:

fine-tuning

Input Output

Input Format:

Llama3 prompt

Accepted Modalities:

text

Output Format:

text

LLM Name	Minerva 3B Llama3 Instruct V0.1
Repository 🤗	https://huggingface.co/mudler/Minerva-3B-Llama3-Instruct-v0.1
Model Size	3b
Required VRAM	5.8 GB
Updated	2026-03-29
Maintainer	mudler
Model Type	mistral
Instruction-Based	Yes
Model Files	2.0 GB: 1-of-3 2.0 GB: 2-of-3 1.8 GB: 3-of-3
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.40.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32768
Torch Data Type	bfloat16

Rank the Minerva 3B Llama3 Instruct V0.1 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Minerva 3B Llama3 Instruct V0.1

Best Alternatives	Context / RAM	Downloads	Likes
Ministral 3B Instruct	128K / 6.7 GB	7607	86
Mistral 3B Instruct V0.2	32K / 11.5 GB	4	4
Minerva 3B Instruct V1.0	16K / 5.8 GB	19	7
Minerva 3B Instruct V1.0	16K / 5.8 GB	12	7
Toffee 3B Beta	8K / 7.7 GB	254	0
Phi 3 Phituguese 3B FP16	4K / 7.6 GB	7	0
Mistral 3B Instruct V0.2 Init	32K / 5.7 GB	589	3

Note: green Score (e.g. "73.2") means that the model is better than mudler/Minerva-3B-Llama3-Instruct-v0.1.