What are the hardware requirements for Barcenas 3.8B?

Barcenas 3.8B requires approximately 7.6 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Barcenas 3.8B and how large is it?

Barcenas 3.8B is developed by Danielbrdz, a model with 3.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Barcenas 3.8B perform on standard benchmarks?

Barcenas 3.8B has the following published scores: MMLU 67.48. Compare against reference models on this page or on the LLM Explorer leaderboards.

Barcenas 3.8B by Danielbrdz — VRAM 7.6GB, 4K context

Name: Barcenas 3.8B
Author: Danielbrdz

Barcenas 3.8B is an open-source language model by Danielbrdz. Features: 3.8b LLM, VRAM: 7.6GB, Context: 4K, License: mit, LLM Explorer Score: 0.14, Arc: 63.5, HellaSwag: 77.6, MMLU: 67.5, GSM8K: 71.3.

Conversational En Endpoints compatible Es Mistral Phi Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Danielbrdz/Barcenas-3.8b

Barcenas 3.8B Benchmarks

ARC: 63.48 vs 96.7 (so35)^-34.4%

HellaSwag: 77.62 vs 95.3 (gpt4)^-18.6%

MMLU: 67.48 vs 88.3 (so35)^-23.6%

GSM8K: 71.34 vs 96.4 (so35)^-26%

LLME Score: 0.14075

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

What is the LLM Explorer Rank (Score)

Barcenas 3.8B (Danielbrdz/Barcenas-3.8b)

🌟 Advertise your project 🚀

Barcenas 3.8B Parameters and Internals

Use Cases

Primary Use Cases:

Spanish conversations

Additional Notes

Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽

Supported Languages

es (fluent), en (fluent)

Training Details

Data Sources:

pinzhenchen/alpaca-cleaned-es

LLM Name	Barcenas 3.8B
Repository 🤗	https://huggingface.co/Danielbrdz/Barcenas-3.8b
Model Size	3.8b
Required VRAM	7.6 GB
Updated	2026-05-21
Maintainer	Danielbrdz
Model Type	mistral
Model Files	5.0 GB: 1-of-2 2.6 GB: 2-of-2
Supported Languages	es en
Model Architecture	MistralForCausalLM
License	mit
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32064
Torch Data Type	float16

Best Alternatives to Barcenas 3.8B

Best Alternatives	Context / RAM	Downloads	Likes
Astral 128K	125K / 7.5 GB	13	1
Zephyrnt 3.8B	32K / 7.5 GB	6	0
Phi 3 Mini 4K Instruct	4K / 7.6 GB	3674	45
Llama Phi 3 DoRA	4K / 7.6 GB	48	6
Mcqa	4K / 7.6 GB	5	0
Phi Pandalm	4K / 7.6 GB	5	0
Hermes	4K / 7.6 GB	3	1
Empty Phi 3 Mini	4K / 7.6 GB	5	0
...i3 Short Story Merged Bfloat16	4K / 7.6 GB	18	1
Phi 3 Mini 4K Mango 2	4K / 7.6 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than Danielbrdz/Barcenas-3.8b.

Rank the Barcenas 3.8B 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

Barcenas 3.8B by Danielbrdz

» All LLMs » Danielbrdz » Barcenas 3.8B URL Share it on

Barcenas 3.8B Benchmarks

Barcenas 3.8B Parameters and Internals

Best Alternatives to Barcenas 3.8B

Rank the Barcenas 3.8B Capabilities

What open-source LLMs or SLMs are you in search of? 53999 in total.