What are the hardware requirements for Llama31 Eros Lora?

Llama31 Eros Lora requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama31 Eros Lora and how large is it?

Llama31 Eros Lora is developed by DeltaIV, 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 Llama31 Eros Lora?

Llama31 Eros Lora is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama31 Eros Lora by DeltaIV — VRAM 0.2GB

Name: Llama31 Eros Lora
Author: DeltaIV

Llama31 Eros Lora is an open-source language model by DeltaIV. Features: 8b LLM, VRAM: 0.2GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.14.

Base model:finetune:grimjim/ll... Base model:grimjim/llama-3.1-8... En Endpoints compatible Instruct Llama Lora Region:us Safetensors Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/DeltaIV/llama31-eros-lora

Llama31 Eros Lora Parameters and Internals

LLM Name	Llama31 Eros Lora
Repository 🤗	https://huggingface.co/DeltaIV/llama31-eros-lora
Base Model(s)	grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
Model Size	8b
Required VRAM	0.2 GB
Updated	2026-09-08
Maintainer	DeltaIV
Instruction-Based	Yes
Model Files	0.2 GB
Supported Languages	en
Model Architecture	AutoModel
License	apache-2.0
Model Max Length	131072
Is Biased	none
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|finetune_right_pad_id\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	o_proj\|v_proj\|q_proj\|down_proj\|up_proj\|k_proj\|gate_proj
LoRA Alpha	16
LoRA Dropout	0
R Param	16

Rank the Llama31 Eros Lora 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 Llama31 Eros Lora

Best Alternatives	Context / RAM	Downloads	Likes
Ur Orpo Adapter	0K / 0.2 GB	18	0
Witcher Llama3 8B Lora	0K / 0 GB	3	2
Abliteration OVA 8B R128 LORA	0K / 0.7 GB	0	1
L3 Unaligned R256 LoRA	0K / 1.5 GB	0	1
AblDWP LoRA	0K / 0.4 GB	0	1
Talktoai	0K / 16.1 GB	0	2
Llama3.1 8b Outline Generation	0K / 0.2 GB	0	1
... Instruct Abliteration LoRA 8B	0K / 0.2 GB	0	9
Llama 3 8B Instruct Checkit	0K / 0.2 GB	0	1
...3 8B Instruct Ct2 Int8 Float16	0K / 8 GB	14	0

Note: green Score (e.g. "73.2") means that the model is better than DeltaIV/llama31-eros-lora.