What are the hardware requirements for Shisa V1 Llama3 8B?

Shisa V1 Llama3 8B requires approximately 16.1 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 Shisa V1 Llama3 8B and how large is it?

Shisa V1 Llama3 8B is developed by shisa-ai, 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 Shisa V1 Llama3 8B?

Shisa V1 Llama3 8B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Shisa V1 Llama3 8B by shisa-ai — VRAM 16.1GB, 8K context

Name: Shisa V1 Llama3 8B
Author: shisa-ai

Shisa V1 Llama3 8B is an open-source language model by shisa-ai. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: llama3, Instruction-Based, LLM Explorer Score: 0.13.

Base model:finetune:meta-llama... Base model:meta-llama/meta-lla... Conversational Dataset:augmxnt/ultra-orca-bor... Endpoints compatible Generated from trainer Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/shisa-ai/shisa-v1-llama3-8b

Shisa V1 Llama3 8B Parameters and Internals

Model Type

LlamaForCausalLM

Additional Notes

Model achieves the best performance with a learning rate of 8e-6. Weight watcher and NEFTune tool usage is indicated.

Training Details

Data Sources:

augmxnt/ultra-orca-boros-en-ja-v1

Methodology:

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct

Context Length:

8192

Hardware Used:

multi-GPU, 8 devices

LLM Name	Shisa V1 Llama3 8B
Repository 🤗	https://huggingface.co/shisa-ai/shisa-v1-llama3-8b
Base Model(s)	Meta Llama 3 8B Instruct meta-llama/Meta-Llama-3-8B-Instruct
Model Size	8b
Required VRAM	16.1 GB
Updated	2026-08-02
Maintainer	shisa-ai
Model Type	llama
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Rank the Shisa V1 Llama3 8B 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 Shisa V1 Llama3 8B

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
Zero Llama 3.1 8B Beta6	1048K / 16.1 GB	7	1

Note: green Score (e.g. "73.2") means that the model is better than shisa-ai/shisa-v1-llama3-8b.