Keural Sft 18K is an open-source language model by mkd-hossain. Features: 15.4b LLM, VRAM: 30.7GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.31.
| LLM Name | Keural Sft 18K |
| Repository 🤗 | https://huggingface.co/mkd-hossain/keural-sft-18k |
| Base Model(s) | |
| Model Size | 15.4b |
| Required VRAM | 30.7 GB |
| Updated | 2026-05-20 |
| Maintainer | mkd-hossain |
| Model Type | mixtral |
| Model Files | |
| Supported Languages | ko en |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 131074 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...eLlama 3x7B Dialect Experts It | 16K / 30.9 GB | 19 | 0 |
| ...alect Experts Random Gate Base | 16K / 30.7 GB | 8 | 0 |
| CodeLlama 3x7B Base | 16K / 30.7 GB | 14 | 0 |
| ...lama 3x7B Dialect Experts Base | 16K / 30.7 GB | 6 | 0 |
🆘 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! 🌟