What are the hardware requirements for Rinna Llama 3 Youko 8B 4bits?

Rinna Llama 3 Youko 8B 4bits requires approximately 6.1 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Rinna Llama 3 Youko 8B 4bits and how large is it?

Rinna Llama 3 Youko 8B 4bits is developed by RichardErkhov, a model with 8b 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 Rinna Llama 3 Youko 8B 4bits?

Rinna Llama 3 Youko 8B 4bits is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Rinna Llama 3 Youko 8B 4bits by RichardErkhov — VRAM 6.1GB, 8K context

Name: Rinna Llama 3 Youko 8B 4bits
Author: RichardErkhov

Rinna Llama 3 Youko 8B 4bits is an open-source language model by RichardErkhov. Features: 8b LLM, VRAM: 6.1GB, Context: 8K, License: llama3, LLM Explorer Score: 0.12.

Arxiv:2404.01657 4-bit Base model:quantized:rinna/lla... Base model:rinna/llama-3-youko... Bitsandbytes Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/RichardErkhov/rinna_-_llama-3-youko-8b-4bits

Rinna Llama 3 Youko 8B 4bits Parameters and Internals

Model Type

text generation

Additional Notes

Quantization made by Richard Erkhov.

Supported Languages

Japanese (high), English (high)

Training Details

Data Sources:

Japanese CC-100, Japanese C4, Japanese OSCAR, The Pile, Wikipedia, rinna curated Japanese dataset

Data Volume:

22B tokens

Methodology:

Continual pre-training

Model Architecture:

32-layer, 4096-hidden-size transformer-based language model

LLM Name	Rinna Llama 3 Youko 8B 4bits
Repository 🤗	https://huggingface.co/RichardErkhov/rinna_-_llama-3-youko-8b-4bits
Base Model(s)	Llama 3 Youko 8B rinna/llama-3-youko-8b
Model Size	8b
Required VRAM	6.1 GB
Updated	2026-05-25
Maintainer	RichardErkhov
Model Type	llama
Model Files	5.0 GB: 1-of-2 1.1 GB: 2-of-2
Supported Languages	ja en
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.2
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	float16

Rank the Rinna Llama 3 Youko 8B 4bits 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 Rinna Llama 3 Youko 8B 4bits

Best Alternatives	Context / RAM	Downloads	Likes
...otron 8B UltraLong 4M Instruct	4192K / 32.1 GB	1135	125
UltraLong Thinking	4192K / 16.1 GB	2	3
...a 3.1 8B UltraLong 4M Instruct	4192K / 32.1 GB	176	24
...a 3.1 8B UltraLong 2M Instruct	2096K / 32.1 GB	875	9
...otron 8B UltraLong 2M Instruct	2096K / 32.1 GB	124	18
Cthulhu 8B V1.4	1048K / 16.1 GB	10	10
...raLong 1M Instruct Abliterated	1048K / 32.1 GB	4	9
...a 3.1 8B UltraLong 1M Instruct	1048K / 32.1 GB	1387	29
...otron 8B UltraLong 1M Instruct	1048K / 32.1 GB	702	59
...xis Bookwriter Llama3.1 8B Sft	1048K / 16.1 GB	25	4

Note: green Score (e.g. "73.2") means that the model is better than RichardErkhov/rinna_-_llama-3-youko-8b-4bits.