What are the hardware requirements for LFM2.5 1.2B Instruct Korean?

LFM2.5 1.2B Instruct Korean requires approximately 2.3 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LFM2.5 1.2B Instruct Korean and how large is it?

LFM2.5 1.2B Instruct Korean is developed by sh-024, a model with 1.2b 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 LFM2.5 1.2B Instruct Korean?

LFM2.5 1.2B Instruct Korean is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 1.2B Instruct Korean by sh-024 — VRAM 2.3GB, 125K context

Name: LFM2.5 1.2B Instruct Korean
Author: sh-024

LFM2.5 1.2B Instruct Korean is an open-source language model by sh-024. Features: 1.2b LLM, VRAM: 2.3GB, Context: 125K, License: other, Instruction-Based, LLM Explorer Score: 0.23.

Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-1.2... Conversational Dataset:carrotai/ko-instructio... Dataset:markrai/kocommercial-d... Dataset:maywell/kovast Endpoints compatible Instruct Instruction-tuned Ko Korean Lfm2 Lfm2.5 Region:us Safetensors Unsloth

Model Card on HF 🤗: https://huggingface.co/sh-024/LFM2.5-1.2B-Instruct-Korean

LFM2.5 1.2B Instruct Korean Parameters and Internals

LLM Name	LFM2.5 1.2B Instruct Korean
Repository 🤗	https://huggingface.co/sh-024/LFM2.5-1.2B-Instruct-Korean
Base Model(s)	LiquidAI/LFM2.5-1.2B-Instruct LiquidAI/LFM2.5-1.2B-Instruct
Model Size	1.2b
Required VRAM	2.3 GB
Updated	2026-07-22
Maintainer	sh-024
Model Type	lfm2
Instruction-Based	Yes
Model Files	2.3 GB
Supported Languages	ko
Model Architecture	Lfm2ForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the LFM2.5 1.2B Instruct Korean 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 LFM2.5 1.2B Instruct Korean

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 1.2B Instruct	125K / 2.3 GB	575331	647
LFM2.5 1.2B Instruct	125K / 2.3 GB	22673	8
...fm2.5 1.2B Instruct Manumit V1	125K / 2.3 GB	139	0
Lfm2.5 1.2B Noval Agentic	125K / 2.3 GB	84	0
Lfm2.5 1.2B Asterion Agentic	125K / 2.3 GB	53	0
...B SFT Claude Reasoning Unsloth	125K / 2.3 GB	492	0
...1.2B Noval Instruct Paramdelta	125K / 2.3 GB	43	0
LFM2.5 1.2B Instruct ONNX	125K / GB	1348	35
... Claude Opus Reasoning Unsloth	125K / 2.3 GB	225	0
... Function Calling XLAM Unsloth	125K / 2.3 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than sh-024/LFM2.5-1.2B-Instruct-Korean.