What are the hardware requirements for Llama 3 8B Samantha?

Llama 3 8B Samantha requires approximately 16.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama 3 8B Samantha and how large is it?

Llama 3 8B Samantha is developed by ruslandev, 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 Llama 3 8B Samantha?

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

Llama 3 8B Samantha by ruslandev — VRAM 16.1GB

Name: Llama 3 8B Samantha
Author: ruslandev

Llama 3 8B Samantha is an open-source language model by ruslandev. Features: 8b LLM, VRAM: 16.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.

4bit Base model:finetune:unsloth/ll... Base model:unsloth/llama-3-8b-... Dataset:cognitivecomputations/... En Endpoints compatible Llama Lora Quantized Region:us Safetensors Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/ruslandev/llama-3-8b-samantha

Llama 3 8B Samantha Parameters and Internals

Model Type

text generation

Training Details

Data Sources:

cognitivecomputations/samantha-data

Methodology:

Finetuned using gptchain framework

Training Time:

1 hour on a single A100

Hardware Used:

A100 GPU

Input Output

Input Format:

Alpaca format with a specific system prompt

LLM Name	Llama 3 8B Samantha
Repository 🤗	https://huggingface.co/ruslandev/llama-3-8b-samantha
Base Model(s)	Llama 3 8B Bnb 4bit unsloth/llama-3-8b-bnb-4bit
Model Size	8b
Required VRAM	16.1 GB
Updated	2026-07-25
Maintainer	ruslandev
Model Files	0.2 GB 5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4
Supported Languages	en
Quantization Type	4bit
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Model Max Length	8192
Is Biased	none
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	v_proj\|q_proj\|down_proj\|k_proj\|gate_proj\|o_proj\|up_proj
LoRA Alpha	16
LoRA Dropout	0
R Param	16

Rank the Llama 3 8B Samantha 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 Llama 3 8B Samantha

Best Alternatives	Context / RAM	Downloads	Likes
Lora Model 1	8K / 5.8 GB	7	0
Llama3 Math Merged4	0K / 22.2 GB	7	0
...3 Project Management Assistant	0K / 0.2 GB	4	3
LLAMA3 Vuln Detection	0K / 0.2 GB	6	0
Educate Ai V2	0K / 0.2 GB	5	0
Llama3 8B Myfine	0K / 16.1 GB	7	0
...ama 3 8B Instruct Bnb Telcom 3	0K / 0.2 GB	6	0
Model Name	0K / 16.1 GB	5	0
Llama30	0K / 16.1 GB	6	0
Llama26	0K / 16.1 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than ruslandev/llama-3-8b-samantha.