What are the hardware requirements for Llamma 3 QG V.2.0?

Llamma 3 QG V.2.0 requires approximately 0.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llamma 3 QG V.2.0 and how large is it?

Llamma 3 QG V.2.0 is developed by shredder-31, 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 Llamma 3 QG V.2.0?

Llamma 3 QG V.2.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llamma 3 QG V.2.0 by shredder-31 — VRAM 0.3GB

Name: Llamma 3 QG V.2.0
Author: shredder-31

Llamma 3 QG V.2.0 is an open-source language model by shredder-31. Features: 8b LLM, VRAM: 0.3GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.

4bit Adapter Base model:adapter:unsloth/lla... Base model:unsloth/llama-3-8b-... En Endpoints compatible Finetuned Gguf Llama Lora Peft Quantized Region:us Safetensors Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/shredder-31/Llamma-3_QG_V.2.0

Llamma 3 QG V.2.0 Parameters and Internals

Model Type

text generation, inference

Supported Languages

en (high)

LLM Name	Llamma 3 QG V.2.0
Repository 🤗	https://huggingface.co/shredder-31/Llamma-3_QG_V.2.0
Base Model(s)	Llama 3 8B Bnb 4bit unsloth/llama-3-8b-bnb-4bit
Model Size	8b
Required VRAM	0.3 GB
Updated	2026-08-05
Maintainer	shredder-31
Model Files	16.1 GB 0.3 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	4bit\|gguf
Model Architecture	Adapter
License	apache-2.0
Model Max Length	8192
Is Biased	none
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|reserved_special_token_250\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	v_proj\|down_proj\|k_proj\|gate_proj\|up_proj\|q_proj\|o_proj
LoRA Alpha	16
LoRA Dropout	0
R Param	32

Rank the Llamma 3 QG V.2.0 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 Llamma 3 QG V.2.0

Best Alternatives	Context / RAM	Downloads	Likes
Unsloth Military Llama3 1	0K / 16.1 GB	30	0
...3 8B Instruct Function Calling	0K / 2.4 GB	35	30
Qwen3 8B Roleplay CN V7	0K / 5 GB	841	0
Soro	0K / 5.8 GB	1107	0
ArGuard Qwen3 VL 8B QLoRA A1	0K / 0.2 GB	17	1
Llama 3.1 8B Sti Anamnese Lora	0K / 0.2 GB	19	1
AegisX1 8B A1B	0K / 0.7 GB	18	3
Llama 3.1 8B PubMedQA QLoRA	0K / 0.2 GB	6	2
Arabic DeepSeek R1 Distill 8B	0K / 0 GB	9	4
Llama 3 8B Muxue 1.0 Lora	0K / 0.2 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than shredder-31/Llamma-3_QG_V.2.0.