What are the hardware requirements for Tiny Ko 187M Sft 250718?

Tiny Ko 187M Sft 250718 requires approximately 0.4 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Tiny Ko 187M Sft 250718 and how large is it?

Tiny Ko 187M Sft 250718 is developed by minpeter, a model with 187m 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 Tiny Ko 187M Sft 250718?

Tiny Ko 187M Sft 250718 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tiny Ko 187M Sft 250718 by minpeter — VRAM 0.4GB, 64K context

Name: Tiny Ko 187M Sft 250718
Author: minpeter

Tiny Ko 187M Sft 250718 is an open-source language model by minpeter. Features: 187m LLM, VRAM: 0.4GB, Context: 64K, Instruction-Based, LLM Explorer Score: 0.19.

Axolotl Base model:finetune:minpeter/t... Base model:minpeter/tiny-ko-18... Conversational Dataset:allenai/tulu-3-sft-per... Dataset:coastral/korean-writin... Dataset:devngho/korean-instruc... Dataset:heegyu/open-korean-ins... Dataset:huggingfacetb/smol-smo... Dataset:lemon-mint/korean-fine... Dataset:lemon-mint/smol-korean... Dataset:trillionlabs/multisyst... Endpoints compatible Generated from trainer Instruct Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/minpeter/tiny-ko-187m-sft-250718

Tiny Ko 187M Sft 250718 Parameters and Internals

LLM Name	Tiny Ko 187M Sft 250718
Repository 🤗	https://huggingface.co/minpeter/tiny-ko-187m-sft-250718
Base Model(s)	Tiny Ko 187M Base 250718 minpeter/tiny-ko-187m-base-250718
Model Size	187m
Required VRAM	0.4 GB
Updated	2026-08-04
Maintainer	minpeter
Model Type	llama
Instruction-Based	Yes
Model Files	0.4 GB 0.0 GB
Model Architecture	LlamaForCausalLM
Context Length	65536
Model Max Length	65536
Transformers Version	4.53.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Tiny Ko 187M Sft 250718 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 Tiny Ko 187M Sft 250718

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3 187M Instruct	8K / 0.7 GB	6	0