What are the hardware requirements for Waktaverse Llama 3 KO 8B Instruct?

Waktaverse Llama 3 KO 8B Instruct 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 Waktaverse Llama 3 KO 8B Instruct and how large is it?

Waktaverse Llama 3 KO 8B Instruct is developed by PathFinderKR, a model with 8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Waktaverse Llama 3 KO 8B Instruct perform on standard benchmarks?

Waktaverse Llama 3 KO 8B Instruct has the following published scores: MMLU 67.21. Compare against reference models on this page or on the LLM Explorer leaderboards.

Waktaverse Llama 3 KO 8B Instruct by PathFinderKR — VRAM 16.1GB, 8K context

Name: Waktaverse Llama 3 KO 8B Instruct
Author: PathFinderKR

Waktaverse Llama 3 KO 8B Instruct is an open-source language model by PathFinderKR. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: llama3, Instruction-Based, LLM Explorer Score: 0.13, Arc: 58.8, HellaSwag: 79.4, MMLU: 67.2, GSM8K: 61.9.

Base model:finetune:meta-llama... Base model:meta-llama/meta-lla... Conversational Dataset:markrai/kocommercial-d... Deploy:azure En Endpoints compatible Instruct Ko Llama Llama-3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/PathFinderKR/Waktaverse-Llama-3-KO-8B-Instruct

Waktaverse Llama 3 KO 8B Instruct Parameters and Internals

Model Type

Large Language Model

Use Cases

Limitations:

Not intended for high-stakes decision-making including medical, legal, or safety-critical applications due to potential risks of relying on automated decision-making.

Supported Languages

Korean (High), English (Medium)

Training Details

Data Sources:

MarkrAI/KoCommercial-Dataset

Methodology:

The model is trained using LoRA for computational efficiency. 0.04 billion parameters (0.51% of total parameters) were trained.

Context Length:

4096

Training Time:

80 hours

Hardware Used:

NVIDIA GeForce RTX 4080 SUPER

Input Output

Performance Tips:

Add Korean system prompt for better output.

LLM Name	Waktaverse Llama 3 KO 8B Instruct
Repository 🤗	https://huggingface.co/PathFinderKR/Waktaverse-Llama-3-KO-8B-Instruct
Base Model(s)	Meta Llama 3 8B Instruct meta-llama/Meta-Llama-3-8B-Instruct
Model Size	8b
Required VRAM	16.1 GB
Updated	2026-07-28
Maintainer	PathFinderKR
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
Supported Languages	ko en
Model Architecture	LlamaForCausalLM
License	llama3
Context Length	8192
Model Max Length	8192
Transformers Version	4.41.2
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	128256
Torch Data Type	float16

Rank the Waktaverse Llama 3 KO 8B Instruct 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 Waktaverse Llama 3 KO 8B Instruct

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 PathFinderKR/Waktaverse-Llama-3-KO-8B-Instruct.