mrtoncl/turkish-han-model
TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 11, 2026Architecture:Transformer Featherless Exclusive Cold
The mrtoncl/turkish-han-model is an 8 billion parameter language model created by mrtoncl through a SLERP merge of Sao10K/L3-8B-Stheno-v3.2 and ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1. This model is specifically designed to enhance performance in Turkish language tasks, leveraging the strengths of its constituent models. With an 8192-token context length, it is optimized for applications requiring robust Turkish language understanding and generation.
Loading preview...
Model Overview
The mrtoncl/turkish-han-model is an 8 billion parameter language model developed by mrtoncl. It was created using the SLERP merge method via mergekit, combining two distinct base models to achieve enhanced capabilities, particularly for the Turkish language.
Key Capabilities
- Turkish Language Focus: This model is specifically engineered by merging
ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1, indicating a strong specialization in Turkish language processing. - Merged Architecture: It integrates
Sao10K/L3-8B-Stheno-v3.2andytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1, aiming to combine their respective strengths. - Context Length: Supports an 8192-token context window, suitable for handling longer texts and more complex queries.
Good For
- Turkish NLP Applications: Ideal for tasks such as text generation, summarization, translation, and conversational AI in Turkish.
- Research and Development: Provides a strong base for further fine-tuning or experimentation with Turkish language models.
- Leveraging Merged Strengths: Users looking for a model that combines the characteristics of the L3-8B-Stheno and Turkish-Llama architectures.