LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Linkbricks Horizon AI Korean Advanced 12B by Saxo

 »  All LLMs  »  Saxo  »  Linkbricks Horizon AI Korean Advanced 12B   URL Share it on

  109   

Linkbricks Horizon AI Korean Advanced 12B is an open-source language model by Saxo. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.16.

Base model:mistralai/mistral-n... Base model:quantized:mistralai...   Cn   Conversational   Dataset:kuotient/gsm8k-ko Dataset:lilacai/glaive-functio... Dataset:maywell/ko ultrafeedba... Dataset:saxo/en ko translation... Dataset:saxo/en ko translation...   Dataset:saxo/ko-news-corpus-1   Dataset:saxo/ko-news-corpus-2   Dataset:saxo/ko-news-corpus-3   Dataset:saxo/ko-news-corpus-4   Dataset:saxo/ko-news-corpus-5   Dataset:saxo/ko-news-corpus-6   Dataset:saxo/ko-news-corpus-7   Dataset:saxo/ko-news-corpus-8   Dataset:saxo/ko-news-corpus-9 Dataset:saxo/ko aspect sentime... Dataset:saxo/ko cn translation... Dataset:saxo/ko government qa ... Dataset:saxo/ko jp translation... Dataset:saxo/ko summarization ... Dataset:saxo/openorca cleaned ... Dataset:youjunhyeok/ko-orca-pa...   En   Endpoints compatible   Gguf   Instruct   Jp   Ko   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Korean-Advanced-12B 

Linkbricks Horizon AI Korean Advanced 12B Benchmarks

LLME Score: 0.15561
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Linkbricks Horizon AI Korean Advanced 12B (Saxo/Linkbricks-Horizon-AI-Korean-Advanced-12B)
🌟 Advertise your project 🚀

Linkbricks Horizon AI Korean Advanced 12B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
AI analytics, Big data analytics
Applications:
High-dimensional analysis of customer reviews and social posts, Coding, Writing, Math, Decision making
Additional Notes 
Enhanced for high-dimensional analysis and logic tasks. Supports Korean Function Call and Tool Calling.
Supported Languages 
ko (proficient), en (proficient), jp (proficient), cn (proficient)
Training Details 
Data Sources:
Saxo/ko_cn_translation_tech_social_science_linkbricks_single_dataset, Saxo/ko_jp_translation_tech_social_science_linkbricks_single_dataset, Saxo/en_ko_translation_tech_science_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/en_ko_translation_social_science_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/ko_aspect_sentiment_sns_mall_sentiment_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/ko_summarization_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/OpenOrca_cleaned_kor_linkbricks_single_dataset_with_prompt_text_huggingface, Saxo/ko_government_qa_total_linkbricks_single_dataset_with_prompt_text_huggingface_sampled, Saxo/ko-news-corpus-1, Saxo/ko-news-corpus-2, Saxo/ko-news-corpus-3, Saxo/ko-news-corpus-4, Saxo/ko-news-corpus-5, Saxo/ko-news-corpus-6, Saxo/ko-news-corpus-7, Saxo/ko-news-corpus-8, Saxo/ko-news-corpus-9, maywell/ko_Ultrafeedback_binarized, youjunhyeok/ko-orca-pair-and-ultrafeedback-dpo, lilacai/glaive-function-calling-v2-sharegpt, kuotient/gsm8k-ko
Data Volume:
10 million Korean news corpus
Methodology:
CPT(Continue-Pretraining)->SFT->DPO
Context Length:
128000
Hardware Used:
8 H100-80G GPUs
Model Architecture:
Uses Mistral-Nemo-Instruct-2407 as a base model; the tokenizer of the base model used without word expansion
Input Output 
Accepted Modalities:
text
LLM NameLinkbricks Horizon AI Korean Advanced 12B
Repository 🤗https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Korean-Advanced-12B 
Base Model(s)  Mistral Nemo Instruct 2407   mistralai/Mistral-Nemo-Instruct-2407
Model Size12b
Required VRAM24.5 GB
Updated2026-04-06
MaintainerSaxo
Model Typemistral
Instruction-BasedYes
Model Files  24.5 GB   7.5 GB   8.7 GB   10.1 GB   13.0 GB   4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesko en jp cn
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.43.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token</s>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Linkbricks Horizon AI Korean Advanced 12B

Best Alternatives
Context / RAM
Downloads
Likes
Geneva 12B GCv2 5M1000K / 24.5 GB413
ReWiz Nemo 12B Instruct1000K / 24.5 GB82
...o Instruct 12B Philosophy Math1000K / 24.5 GB91
...omix Unleashed 12B V0.6.1 8bit1000K / 12.9 GB42
Ava 1.0 12B1000K / 24.5 GB344
Poemma 12B1000K / 24.5 GB62
...t RP Noodles 12B V1.4 EXL2 8.01000K / 12.5 GB342
...orean Mistral Nemo Sft DPO 12B1000K / 24.5 GB1877
Lumimaid Magnum 12B EXL2 8.01000K / 12.6 GB274
DeepOpus 1 12B Preview128K / 24.5 GB180
Note: green Score (e.g. "73.2") means that the model is better than Saxo/Linkbricks-Horizon-AI-Korean-Advanced-12B.

Rank the Linkbricks Horizon AI Korean Advanced 12B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer