Linkbricks Horizon AI Korean Mistral Nemo Sft DPO 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: 0.15.
Base model:mistralai/mistral-n... Base model:quantized:mistralai... Cn Conversational Dataset:maywell/ko ultrafeedba... Dataset:saxo/en ko translation... Dataset:saxo/en ko translation... 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 ... En Endpoints compatible Ggml Gguf Instruct Jp Ko Mistral Q4 Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Korean-Mistral-Nemo-sft-dpo-12B
Linkbricks Horizon AI Korean Mistral Nemo Sft DPO 12B Benchmarks
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 Mistral Nemo Sft DPO 12B Parameters and Internals
| LLM Name | Linkbricks Horizon AI Korean Mistral Nemo Sft DPO 12B |
| Repository 🤗 | https://huggingface.co/Saxo/Linkbricks-Horizon-AI-Korean-Mistral-Nemo-sft-dpo-12B |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2026-05-26 |
| Maintainer | Saxo |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ko en jp cn |
| GGML Quantization | Yes |
| GGUF Quantization | Yes |
| Quantization Type | ggml|q4|gguf|q4_k|q5_k |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.43.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | </s> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Linkbricks Horizon AI Korean Mistral Nemo Sft DPO 12B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Horizon AI Korean Advanced 12B | 1000K / 24.5 GB | 170 | 1 |
| Geneva 12B GCv2 5M | 1000K / 24.5 GB | 20 | 13 |
| ReWiz Nemo 12B Instruct | 1000K / 24.5 GB | 11 | 2 |
| ...o Instruct 12B Philosophy Math | 1000K / 24.5 GB | 9 | 1 |
| ...omix Unleashed 12B V0.6.1 8bit | 1000K / 12.9 GB | 4 | 2 |
| Ava 1.0 12B | 1000K / 24.5 GB | 34 | 4 |
| Poemma 12B | 1000K / 24.5 GB | 2 | 2 |
| ...t RP Noodles 12B V1.4 EXL2 8.0 | 1000K / 12.5 GB | 34 | 2 |
| Lumimaid Magnum 12B EXL2 8.0 | 1000K / 12.6 GB | 27 | 4 |
| DeepOpus 1 12B Preview | 128K / 24.5 GB | 18 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Saxo/Linkbricks-Horizon-AI-Korean-Mistral-Nemo-sft-dpo-12B .
Rank the Linkbricks Horizon AI Korean Mistral Nemo Sft DPO 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! 🌟
What open-source LLMs or SLMs are you in search of? 53999 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 v20260328a