What are the hardware requirements for Q4 Llama 3?

Q4 Llama 3 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 Q4 Llama 3 and how large is it?

Q4 Llama 3 is developed by piyushsalunke, a model with 4.6b 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 Q4 Llama 3?

Q4 Llama 3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Q4 Llama 3 by piyushsalunke — VRAM 6.1GB, 8K context

Name: Q4 Llama 3
Author: piyushsalunke

Q4 Llama 3 is an open-source language model by piyushsalunke. Features: 4.6b LLM, VRAM: 6.1GB, Context: 8K, Quantized, LLM Explorer Score: 0.13.

Arxiv:1910.09700 4-bit Autotrain compatible Bitsandbytes Endpoints compatible Llama Lora Q4 Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/piyushsalunke/q4-llama-3

Q4 Llama 3 Parameters and Internals

LLM Name	Q4 Llama 3
Repository 🤗	https://huggingface.co/piyushsalunke/q4-llama-3
Model Size	4.6b
Required VRAM	6.1 GB
Updated	2024-10-29
Maintainer	piyushsalunke
Model Type	llama
Model Files	5.0 GB: 1-of-2 1.1 GB: 2-of-2
Quantization Type	q4
Model Architecture	LlamaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.41.2
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
LoRA Model	Yes
Torch Data Type	float16

Rank the Q4 Llama 3 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 Q4 Llama 3

Best Alternatives	Context / RAM	Downloads	Likes
Llama3 Finetune 4bit	8K / 6.1 GB	0	0
TinyLLama V0	2K / 0 GB	231176	45
SimpleLlamaSentences	2K / 0 GB	6	0
UniversalNER TinyLLama	2K / 0 GB	10	1
UniversalNER TinyLLama	2K / 0 GB	6	1

Note: green Score (e.g. "73.2") means that the model is better than piyushsalunke/q4-llama-3.