oxalis-ink/shamrock-0-e4b

VISIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 20, 2026License:cc-by-nc-4.0Architecture:Transformer Open Weights Featherless Exclusive Cold

shamrock-0-e4b is a 7.9 billion parameter Gemma 4 E4B model fine-tuned by Oxalis for language learning applications, specifically targeting Japanese, Korean, and Simplified Chinese. It features a 32768-token context length and is optimized for tasks like camera translation, text translation, tutoring, and conversational practice within the Oxalis desktop app. The model includes a multi-token-prediction drafter for speculative decoding, enhancing performance in its specialized language-learning use cases.

Loading preview...

shamrock-0-e4b: Language Learning Model for East Asian Languages

shamrock-0-e4b is a 7.9 billion parameter model, fine-tuned from Google DeepMind's Gemma 4 E4B, specifically for language learning applications within the Oxalis desktop app. This model is optimized for Japanese, Korean, and Simplified Chinese, supporting a 32768-token context length.

Key Capabilities

  • Specialized Language Learning: Fine-tuned for core language learning surfaces including camera translation, text translation, tutor interactions, conversational practice, and dictionary lookups.
  • Multilingual Focus: Optimized for high performance in Japanese, Korean, and Simplified Chinese.
  • Efficient Decoding: Incorporates a multi-token-prediction (MTP) drafter for speculative decoding, enhancing generation speed and efficiency.
  • GGUF Compatibility: Provided in GGUF format, including q4_k_m quantization for the main model and f16 for the mmproj component, suitable for llama.cpp runtimes.

Good For

  • Integrating into Language Learning Applications: Ideal for developers building applications focused on East Asian language acquisition.
  • Offline Language Processing: Suitable for desktop applications requiring efficient, localized language model capabilities.
  • Research in Fine-tuning for Specific Domains: Provides a case study for fine-tuning general-purpose models for niche applications like language education.

Finetunes
1 models