What are the hardware requirements for Ko Llama 46M Random?

Ko Llama 46M Random requires approximately 0.3 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Ko Llama 46M Random and how large is it?

Ko Llama 46M Random is developed by heegyu, a model with 46m 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 Ko Llama 46M Random?

Ko Llama 46M Random is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Ko Llama 46M Random by heegyu — VRAM 0.3GB, 2K context

Name: Ko Llama 46M Random
Author: heegyu

Ko Llama 46M Random is an open-source language model by heegyu. Features: 46m LLM, VRAM: 0.3GB, Context: 2K, LLM Explorer Score: 0.11.

Arxiv:1910.09700 Endpoints compatible Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/heegyu/ko-llama-46M-random

Ko Llama 46M Random Parameters and Internals

LLM Name	Ko Llama 46M Random
Repository 🤗	https://huggingface.co/heegyu/ko-llama-46M-random
Model Size	46m
Required VRAM	0.3 GB
Updated	2026-05-06
Maintainer	heegyu
Model Type	llama
Model Files	0.3 GB
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.38.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	46160
Torch Data Type	float32

Rank the Ko Llama 46M Random 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 Ko Llama 46M Random

Best Alternatives	Context / RAM	Downloads	Likes
Nuevamol 46M Base	8K / 0.1 GB	23	0

Note: green Score (e.g. "73.2") means that the model is better than heegyu/ko-llama-46M-random.