What are the hardware requirements for Llm Jp 3 3.7B Instruct EZO Humanities?

Llm Jp 3 3.7B Instruct EZO Humanities 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 Llm Jp 3 3.7B Instruct EZO Humanities and how large is it?

Llm Jp 3 3.7B Instruct EZO Humanities is developed by AXCXEPT, a model with 3.7b 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 Llm Jp 3 3.7B Instruct EZO Humanities?

Llm Jp 3 3.7B Instruct EZO Humanities is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llm Jp 3 3.7B Instruct EZO Humanities by AXCXEPT — VRAM 7.6GB, 4K context

Name: Llm Jp 3 3.7B Instruct EZO Humanities
Author: AXCXEPT

Llm Jp 3 3.7B Instruct EZO Humanities is an open-source language model by AXCXEPT. Features: 3.7b LLM, VRAM: 7.6GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.14.

Conversational En Endpoints compatible Instruct Ja Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/AXCXEPT/llm-jp-3-3.7b-instruct-EZO-Humanities

Llm Jp 3 3.7B Instruct EZO Humanities Parameters and Internals

Model Type

text generation, conversational

Additional Notes

This model is considered an experimental prototype, intended for research and development only.

Supported Languages

en (proficient), ja (proficient)

Training Details

Data Sources:

Japanese Wikipedia, FineWeb

Methodology:

plain instruction tuning

Training Time:

Hardware Used:

A100 × 8

LLM Name	Llm Jp 3 3.7B Instruct EZO Humanities
Repository 🤗	https://huggingface.co/AXCXEPT/llm-jp-3-3.7b-instruct-EZO-Humanities
Model Size	3.7b
Required VRAM	7.6 GB
Updated	2026-09-16
Maintainer	AXCXEPT
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 2.6 GB: 2-of-2
Supported Languages	en ja
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.45.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<PAD\|LLM-jp>
Vocabulary Size	99584
Torch Data Type	bfloat16

Rank the Llm Jp 3 3.7B Instruct EZO Humanities 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 Llm Jp 3 3.7B Instruct EZO Humanities

Best Alternatives	Context / RAM	Downloads	Likes
SJT 3.7B	4K / 8.2 GB	9	0
....0 Computer Crime Act Instruct	4K / 13.7 GB	9	0
Llm Jp 3 3.7B Instruct	4K / 7.6 GB	1020	13
Llm Jp 3 3.7B Instruct	4K / 7.6 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than AXCXEPT/llm-jp-3-3.7b-instruct-EZO-Humanities.