Linkbricks Horizon AI Korean Superb 27B is an open-source language model by Saxo. Features: 27b LLM, VRAM: 54.8GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.29.
Base model:finetune:google/gem... Base model:google/gemma-2-27b-... 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 Gemma2 Jp Ko Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B
Linkbricks Horizon AI Korean Superb 27B Benchmarks
MMLU Pro: 40.52
GPQA: 14.65
MUSR: 19.53
BBH: 50.61
IFEval: 77.68 vs 88 (so35)-11.7%
MATH Lvl 5: 27.19
LLME Score: 0.28689
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Linkbricks Horizon AI Korean Superb 27B Parameters and Internals
| LLM Name | Linkbricks Horizon AI Korean Superb 27B |
| Repository 🤗 | https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 54.8 GB |
| Updated | 2026-03-15 |
| Maintainer | Saxo |
| Model Type | gemma2 |
| Model Files | |
| Supported Languages | ko en jp cn |
| Model Architecture | Gemma2ForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.46.1 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Linkbricks Horizon AI Korean Superb 27B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ATOMIS | 32K / 66 GB | 5 | 5 |
| SystemGemma2 27B It | 32K / 54.7 GB | 96 | 1 |
| SystemGemma2 27B It | 32K / 54.7 GB | 42 | 3 |
| Gemma 2 27B It | 8K / 54.7 GB | 150241 | 550 |
| ...izon AI Korean Avengers V3 27B | 8K / 54.8 GB | 11 | 0 |
| ...izon AI Korean Avengers V2 27B | 8K / 54.8 GB | 13 | 0 |
| Gemma2Slerp2 27B | 8K / 54.8 GB | 4 | 1 |
| GemmaStock1 27B | 8K / 54.8 GB | 6 | 0 |
| Gemma2Slerp3 27B | 8K / 54.8 GB | 10 | 0 |
| Gemma2Slerp4 27B | 8K / 54.8 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B .
Rank the Linkbricks Horizon AI Korean Superb 27B 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! 🌟
What open-source LLMs or SLMs are you in search of? 51634 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20241124