What are the hardware requirements for Llm Jp 13B V2.0?

Llm Jp 13B V2.0 requires approximately 27.4 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 13B V2.0 and how large is it?

Llm Jp 13B V2.0 is developed by llm-jp, a model with 13b 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 13B V2.0?

Llm Jp 13B V2.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llm Jp 13B V2.0 by llm-jp — VRAM 27.4GB, 4K context

Name: Llm Jp 13B V2.0
Author: llm-jp

Llm Jp 13B V2.0 is an open-source language model by llm-jp. Features: 13b LLM, VRAM: 27.4GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.12.

Deploy:azure En Ja Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/llm-jp/llm-jp-13b-v2.0

Llm Jp 13B V2.0 Parameters and Internals

Model Type

Transformer-based Language Model, text-generation

Use Cases

Areas:

research, commercial applications

Limitations:

The models have not been tuned to ensure outputs align with human intent and safety considerations.

Considerations:

The models are still in the early stages of development.

Supported Languages

en (fluent), ja (fluent)

Training Details

Data Sources:

Japanese Wikipedia, Common Crawl, English Wikipedia, The Pile, The Stack

Data Volume:

256 billion tokens

Context Length:

4096

Hardware Used:

128 A100 40GB GPUs, 8 A100 40GB GPUs

Model Architecture:

Transformer-based

Input Output

Input Format:

text prompt

Accepted Modalities:

text

Output Format:

text

LLM Name	Llm Jp 13B V2.0
Repository 🤗	https://huggingface.co/llm-jp/llm-jp-13b-v2.0
Model Size	13b
Required VRAM	27.4 GB
Updated	2026-08-07
Maintainer	llm-jp
Model Type	llama
Model Files	10.0 GB: 1-of-3 9.9 GB: 2-of-3 7.5 GB: 3-of-3
Supported Languages	en ja
Model Architecture	LLaMAForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad\|LLM-jp>
Vocabulary Size	97024
Torch Data Type	bfloat16

Rank the Llm Jp 13B V2.0 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 13B V2.0

Best Alternatives	Context / RAM	Downloads	Likes
Alpaca 13B	0K / 52.1 GB	73	108
Decapoda Research Llama 13B	0K / 41 GB	10	0
LIMA 13B	0K / 42 GB	78	1
Alpaca 13B	0K / 52.1 GB	426	109
Llama 13B	0K / 42 GB	96	1
Vicuna2	0K / 0 GB	9	16
Vicuna2	0K / 0 GB	5	16
Llama 13B	0K / 42 GB	12	3
... X Alpaca 13B Native 4bit 128g	0K / 7.9 GB	106	727
... X Alpaca 13B Native 4bit 128g	0K / 8.1 GB	10	2

Note: green Score (e.g. "73.2") means that the model is better than llm-jp/llm-jp-13b-v2.0.