What are the hardware requirements for Kori 390M?

Kori 390M requires approximately 0.8 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 Kori 390M and how large is it?

Kori 390M is developed by aixk, a model with 390m 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 Kori 390M?

Kori 390M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kori 390M by aixk — VRAM 0.8GB, 8K context

Name: Kori 390M
Author: aixk

Kori 390M is an open-source language model by aixk. Features: 390m LLM, VRAM: 0.8GB, Context: 8K, Quantized, LLM Explorer Score: 0.24.

En Endpoints compatible Gguf Ko Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/aixk/Kori-390M

Kori 390M Parameters and Internals

LLM Name	Kori 390M
Repository 🤗	https://huggingface.co/aixk/Kori-390M
Model Size	390m
Required VRAM	0.8 GB
Updated	2026-07-24
Maintainer	aixk
Model Type	llama
Model Files	0.8 GB 0.8 GB 0.0 GB
Supported Languages	en ko
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	LlamaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	5.0.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Vocabulary Size	49152

Rank the Kori 390M 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 Kori 390M

Best Alternatives	Context / RAM	Downloads	Likes
TriLM 390M Unpacked	2K / 0.8 GB	68	1